📰 AI 资讯
最新 AI 行业动态、产品发布和技术前沿
寻找 AI 原生时代创业者：极客部落 OPC 入驻招募启动！
点击查看原文>
小扎“消失”三年后发帖，只为它：Meta最强Agent模型进军编程，从免费开源到卖“低价”模型
点击查看原文>
Zig Creator Calls Spade a Spade, Anthropic Blows Smoke
Comments
Agent专用搜索登顶Product Hunt，Token更省搜得更准
出自中国团队
从“三天拆盲盒”到一行命令即用：这群开发者如何改写Agent框架的部署难题？
点击查看原文>
AI推理成本首次算清：GPU利用率不到52%，千万别自建！
点击查看原文>
数据中心用电量占到了爱尔兰用电量的 23%
爱尔兰中央统计局 (CSO) 的数据显示，2025 年数据中心用电量占到了爱尔兰用电量的 23%。而在 2015 年这一比例仅为 5%。大型数据中心的用电量在 2025 年增长了 10%，从 2024 年的 6973 GWh 增至 2025 年的 7663 GWh，所有其他部门同期的用电量仅增长 2%。相比下城市居民用电量占总用电量的 18%，农村居民用电量则为 9%。类似其它地区，爱尔兰也出现了反数据中心抗议活动。该国拥有逾 80 个数据中心。
他们窃取了数据和民主
1998 年时任 Novell CEO 施密特（Eric Schmidt）接受 BBC 采访，当被询问到硅谷的政治立场时，施密特毫不犹豫的咆哮道：“我们反政府、反监管、反国会。”BBC 说，“你们想要的实际上是一个丛林社会？一个强者生存，弱者无依无靠的社会？”施密特坦然称是并以此为傲。硅谷精英想要不受监管的权力，这一论调与一个世纪前的镀金时代寡头如出一辙。而硅谷精英仅仅通过声称对人类传播、信息完整性、真相的命运以及信息文明中知识分布的全球历史性变革拥有实验权威，便得以为所欲为。一场持续数十年、至今仍在进行的实验拉开了序幕。作为监控资本主义的代表，Google 收集的用户数据远远超过其服务的需要。信息无政府状态正在重塑世界政治格局。虚假信息、极化和选举失能都有利于专制，而在追求人类数据的过程中，算法对腐化信息的优先推送有利于其商业利益，能吸引用户参与并引发数据爆炸式增长。任何民主制度都无法在这种环境下长久生存。今天的信息空间与民主制度的公共广场原型截然不同，让民主国家面临持续的压力。生成式 AI 就是以监控资本主义积累的海量数据为食物，而 AI 公司更是无视道德和法律毫无顾忌的窃取数据。
红帽决定聚焦中国企业的“多模型、多GPU、多云”选择权
点击查看原文>
MiniMax CEO称不再领取薪酬，将4%股份激励团队；吐槽DeepSeek面试的华为天才少年回应被控诈骗；宇树机器人给猪做手术登上Nature｜AI周报
点击查看原文>
从看见问题到解决问题，Agent 正重新定义可观测？
点击查看原文>
Agent要数量也要脑子！浪潮信息一边单柜养4万Agent，一边让大模型组队答题
同时发布CPU原生液冷整机柜、多模融合超节点
Linus Torvalds 谈 AI 和垃圾补丁
Linus Torvalds 曾说过大模型（LLM）会让程序员的生产力提升十倍。他在 2026 年印度开源峰会上说，这个数字并不科学，是他随口胡扯的。他说如今的希望是 LLM 给程序员带来的生产力提升能超过其造成的生产力损失。他说，大模型生成的垃圾远多于有用代码，而 AI 生成的 bug 报告浪费了维护者大量的时间精力。Torvalds 称大量 LLM 生成的补丁是无意义的创可贴，或许能解决当前问题，但类似 bug 仍然留在那里，随时可能在其他地方再次出现。他称自己会用 LLM 制作原型，LLM 生成的代码并不能直接使用，但是一个尝试新想法的好方法。他认为 LLM 还无法生成修复内核 bug 的补丁。
UniRL：统一多模态 RL 框架的 2.4X 端到端性能优化实践｜AICon深圳
点击查看原文>
Circle CI推出Chunk Sidecars，将CI校验直接引入AI编码工作流
点击查看原文>
WAIC特别关注｜思想者论坛：当赛道疯狂内卷，谁在拆解AI底层的底层？
< img id="wx_img" src="https://www.qbitai.com/wp-content/uploads/imgs/qbitai-logo-1.png" width="400" height="400">
从前沿创新到产业落地：西门子将亮相2026世界人工智能大会
< img id="wx_img" src="https://www.qbitai.com/wp-content/uploads/imgs/qbitai-logo-1.png" width="400" height="400">
WAIC’26探展召集令！和量子位一起逛展、直播、聊AI
< img id="wx_img" src="https://www.qbitai.com/wp-content/uploads/imgs/qbitai-logo-1.png" width="400" height="400">
Claude Code砸的坑，蚂蚁安全在尝试填上
最新开源两大安全框架
🔥 新增结构化 AI 使用记录：开源无代码 / 低代码平台 NocoBase
汇总一周产品更新日志，最新发布可前往我们的博客查看。 NocoBase 目前更新包括三个分支：main、next 和 develop。 main：截至目前最稳定的版本，推荐安装此版本。 next：包含即将发布的新功能，经过初步测试的版本，可能存在部分已知或未知问题。主要面向测试用户，用于收集反馈和进一步优化功能。适合愿意提前体验新功...
GPT-5.6刚发布，OpenAI安全主管就跑路了？？
两年内走的第六个
CNCF发布招商银行AI调度平台案例 源于范式的HAMi技术获生产级验证
< img id="wx_img" src="https://www.qbitai.com/wp-content/uploads/imgs/qbitai-logo-1.png" width="400" height="400">
Interval Certifications for Multilayered Perceptrons via Lattice Traversal
arXiv:2607.08773v1 Announce Type: new Abstract: In this work we present a rigorous theoretical framework to a foundational problem of AI safety, namely adversarial robustness. In particular, we show that the adversarial robustness problem can be reduced to a lattice traversal problem. Each element of this lattice corresponds to an interval, i.e., an axis-aligned hyper-rectangle, containing an input point $\mathbf{x}$. Consider a multilayered perceptron classifier (MLP). An interval $I$ constitu
CogniConsole: Externalizing Inference-Time Control as a Formal Abstraction for Reliable LLM Interactions
arXiv:2607.08774v1 Announce Type: new Abstract: Reliability in large language model (LLM) systems is typically framed as a function of model capability. We challenge this by demonstrating that reliability is significantly influenced by \emph{inference-time control} -- the computational layer governing task framing and context selection. We introduce \emph{CogniConsole}, an architectural instantiation that externalizes this control into a structured interface combining programmatic coordination
GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning
arXiv:2607.08894v1 Announce Type: new Abstract: Large Language Model (LLM) agents have shown promise in multi-step planning tasks, but existing approaches like LATS (Language Agent Tree Search) and ReAct rely heavily on LLM inference during planning, leading to high computational costs and stochastic behavior. We present \textbf{GATS} (Graph-Augmented Tree Search), a planning framework that combines systematic UCB1-based tree search with a layered world model to eliminate LLM calls during infer
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
arXiv:2607.08964v1 Announce Type: new Abstract: AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple problems that finish within minutes and are evaluated only by their final outcome. This setup overlooks intermediate progress and partial solutions, yielding sparse reward signals and an incomplete picture of agent capability. We introduce Long-Horizon-Terminal-Bench, a terminal benchmark of 46 long-ho
A Formalization of the Mean-Field Derivation of the Vlasov Equation: AI-Assisted Lean Formalization as a Strategy Game
arXiv:2607.08986v1 Announce Type: new Abstract: We formalize a research result in the Lean 4 proof assistant by having a mathematician direct an AI system, and frame the activity as a formalization game. The objective is to turn a LaTeX document into Lean. The game is won when the development compiles, contains no sorry, and a machine check shows the target theorems rest on Lean's foundational axioms alone. Reuse is a second check, by a definition we introduce: whether the development yields a
ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning
arXiv:2607.09059v1 Announce Type: new Abstract: We present ARCANA, a collaborative multi agent framework for solving ARC AGI 2 tasks under strict test time and hardware constraints. ARCANA decomposes each task into iterative perception, hypothesis generation, symbolic execution, and reflective refinement. A perceptual grounding agent builds object centric scene graphs from raw grids, a latent program policy proposes diverse DSL programs, a symbolic executor verifies candidates on demonstrations
Neuro-Agentic Control: A Deep Learning-based LLM-Powered Agentic AI Framework for Controlling Security Controls
arXiv:2607.09076v1 Announce Type: new Abstract: Cyberattacks on operational technology are increasingly causing costly downtime and physical damage, exposing the limitations of traditional rule-based monitoring in industrial IoT environments. While Large Language Models (LLMs) have strong semantic reasoning abilities to assist in decision support, their hallucinatory nature presents unacceptable safety liabilities for closed-loop control. This paper introduces a neuro-agentic control framework,
L-MAD: A Systematic Evaluation of Multi-Agent Debate Structures in Legal Reasoning
arXiv:2607.09099v1 Announce Type: new Abstract: While multi-agent debate (MAD) frameworks have shown significant potential in general reasoning, their effectiveness in highly structured, knowledge-heavy legal domains remains under-explored. In this work, we introduce the Legal Multi-Agent Debate (L-MAD) framework to systematically evaluate different debate structures and aggregation methods within Legal Textual Entailment. By assigning distinct expert personas to multiple agents, L-MAD improves
MedRealMM: A Real-World Multimodal Benchmark for Chinese Online Medical Consultation
arXiv:2607.09142v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in online medical consultation, yet existing benchmarks remain poorly aligned with real clinical practice. Many rely on synthetic conversations or patient simulators, omit patient-uploaded medical images, or evaluate open-ended clinical responses using multiple-choice or lexical-overlap metrics that poorly reflect clinical quality. We introduce \textbf{MedRealMM}, a large-scale benchmark for m
KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling
arXiv:2607.09153v1 Announce Type: new Abstract: Process Reward Models (PRMs) have been proven to be highly effective in guiding test-time scaling (TTS) methods, which significantly boost the capabilities of LLM-based multi-agent systems. However, existing PRMs are text-based: they re-encode the entire trajectory text from scratch. In long multi-agent rollouts, the scoring cost, growing quadratically with respect to sequence length L, creates a severe computational bottleneck, severely limiting
Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distribution Shift
arXiv:2607.09175v1 Announce Type: new Abstract: Deployed LLM agents rely on agentic context, the model-external textual control content assembled by an operational harness. In this work, the mutable component of that context is a persistent system-level instruction that is updated from operational experience while the model, tools, and harness remain fixed. Over long evolution horizons, flat-text maintenance makes verification increasingly difficult as accumulated instructions grow and interact
Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents
arXiv:2607.09195v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly expected to play a central role in AI-driven scientific discovery. Equipped with broad knowledge, flexible reasoning, and tool use, they have the potential to autonomously explore and solve scientific problems by repeatedly proposing hypotheses, testing them, and revising their beliefs in the light of the evidence. In current agents, however, these hypotheses, tests, and belief updates are buried
OpenProver: Agentic and Interactive Theorem Proving with Lean 4
arXiv:2607.09217v1 Announce Type: new Abstract: In this system paper, we present OpenProver, an open-source system for LLM-driven automated theorem proving (ATP) with integrated Lean 4 formal verification. OpenProver integrates a Planner-Worker-Verifier architecture inspired by recent ATP agentic systems such as Aletheia. A Planner agent maintains a compact Whiteboard scratchpad and an unbounded Repository of intermediate findings, and decomposes mathematical work into parallel Workers. OpenP
LongMedBench: Benchmarking Medical Agents for Long-Horizon Clinical Decision-Making
arXiv:2607.09322v1 Announce Type: new Abstract: In this work, we introduce LongMedBench, a real-world EHR-based benchmark for long-horizon clinical decision-making. Prior evaluations of LLM-based medical agents have largely emphasized short-context knowledge QA and tool use. However, real-world medical care is inherently longitudinal, and clinicians must aggregate evidence across repeated visits, tests, and evolving treatments. Therefore, long-horizon interaction is essential for realistic asse
Communication-Efficient Digital-Twin Coordination for Heterogeneous LLM Embodied Agents over Computing Power Networks
arXiv:2607.09330v1 Announce Type: new Abstract: Embodied agent teams powered by heterogeneous large language models (LLMs) are being widely deployed in physical artificial intelligence such as smart factories, warehouses, and service robotics. To enable collaboration among such an agent team, efficient coordination mechanisms that operate reliably under limited network resources are required. However, existing heterogeneous LLM-agent coordination frameworks that rely on multi-round natural-lang
Fictional Worldbuilding: Multi-Agent LLM Collaboration with Hierarchical Context Compression and Iterative Review
arXiv:2607.09403v1 Announce Type: new Abstract: Worldbuilding, the construction of coherent fictional worlds, is a foundational task in game design and literary creation. Large Language Models (LLMs) offer new possibilities for automated content generation, but their application to worldbuilding faces three challenges: context explosion that grows linearly with the building process, the tension between creative diversity and content consistency, and the absence of automated quality assurance. T
How Does Bayesian Causal Discovery Fail? Characterising Structural Consequences in Linear Gaussian Networks under Latent Confounding
arXiv:2607.09449v1 Announce Type: new Abstract: Bayesian causal discovery is widely used for its ability to quantify epistemic uncertainty over directed acyclic graphs (DAGs) through posterior inference. However, its behaviour under latent confounding remains poorly understood, as existing work typically notes that confounding breaks identifiability without characterising how the posterior distribution over DAGs responds. In this work, we analyse posterior behaviour under latent confounding in
ProofCouncil: An LLM Agent for Solving Open Mathematical Problems
arXiv:2607.09474v1 Announce Type: new Abstract: Large language models (LLMs) have shown increasing promise in solving open problems in mathematics. However, their performance can be further improved through agentic workflows tailored to real-world mathematical practice. To this end, we introduce ProofCouncil, a mathematical agent that is designed to tackle open problems using an author-critic architecture. ProofCouncil served as a submission to the second batch of FirstProof, a challenge consis
Ceci n'est pas une pipe: AI systems as semantic abstractions
arXiv:2607.09489v1 Announce Type: new Abstract: An AI system's output is not the fact or world state it appears to describe, but rather an engineered representation. We propose a semantic framework to describe AI systems, to be able to examine the correctness of such representations. To do so, we distinguish what is justified by accepted domain knowledge, what reference sources say, and what the system can currently use. This allows us to give precise definitions to common failures: extrapolati
Multimodal Reward Hacking in Reinforcement Learning
arXiv:2607.09492v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly used to align multimodal large language models (MLLMs), but higher rewards do not always imply better task performance. This risk is amplified when visual evidence is evaluated by text-only or weakly grounded rewards. We study reward hacking in MLLM RL across safety VQA, chart VQA, and stress-test settings, varying reward design, data ambiguity, model scale (2B-32B), and RL algorithm (GRPO, RLOO, DAPO).
HALO: Hybrid Adaptive Latent Reasoning for Language Models
arXiv:2607.08775v1 Announce Type: new Abstract: We study how to improve a frozen pretrained language model with a small amount of adaptive extra computation. A simple approach is to add additional refinement steps on top of the backbone hidden states, but fixed extra refinement can be wasteful: a one-step refinement head may be too weak, while forcing a second full-sequence refinement step everywhere can increase compute without improving transfer. We introduce HALO, a hybrid adaptive latent-re
An Emergent Mirage: Is Emergent Misalignment and Realignment Indeed a Robust Phenomenon?
arXiv:2607.09053v1 Announce Type: new Abstract: Recent work has reported Emergent Misalignment (EM), where language models fine-tuned on narrow, domain-specific misaligned datasets abruptly acquire broadly misaligned behavior, alongside evidence that this behavior can be reversed through limited realignment. We systematically study repeated alignment and misalignment cycles using controlled fine-tuning loops while tracking behavioral performance, and LoRA representations throughout training. Al
AgentKGV: Agentic LLM-RAG Framework with Two-Stage Training for the Fact Verification of Knowledge Graphs
arXiv:2607.09092v1 Announce Type: new Abstract: Knowledge graphs (KGs) are often automatically constructed from large-scale corpora, but they inevitably contain factual errors due to noisy sources and extraction failures, and verifying them reliably at industrial scale remains a critical challenge. To address this, we propose AgentKGV, the Agentic LLM-RAG framework for KG fact Verification, that integrates dynamic routing and iterative query rewriting, which handles surface-form mismatch in doc
PRecG: Legal Precedent Retrieval with Graph Neural Networks and Rhetorical Role Segmentation
arXiv:2607.09094v1 Announce Type: new Abstract: Legal precedent retrieval is a fundamental task in legal case preparation, planning, litigation strategy, and legal research. Current approaches for automatic precedent retrieval map legal documents to a low-dimensional semantic space and compute similarity based on the proximity of their representations. These approaches treat legal documents as monolithic texts, ignoring the rhetorical organization of the legal technicalities. Ergo, they overloo
Augmenting Fundamental Analysis with Large Language Models: A RAG-Based System for Generating Investor Briefs
arXiv:2607.09121v1 Announce Type: new Abstract: In this study, we examine the opportunities brought by Large Language Models (LLMs) to various aspects of fundamental analysis of companies based on their reports as well as data and documents describing macroeconomic situation like GDP and inflation changes as well as documents filled to the U.S. Securities and Exchange Commission (SEC) which can be found in EDGAR. We were preprocessing those data and than sending via API to gpt-4o model in a Ret
Complexity-Guided Component-wise Initialization for Language Model Pretraining
arXiv:2607.09204v1 Announce Type: new Abstract: Pretrained language models often exhibit structured weight spectra, suggesting that training may repeatedly produce similar layerwise and component-wise organization. We ask whether these recurring spectral patterns can be reused as an initialization signal for GPT-2-style language-model pretraining. First, we analyze eleven pretrained GPT-2-style checkpoints that vary in size, language, tokenizer, and training corpus, measuring Frobenius norm and
Letter Lemmatization: One-to-one and Banded RNNs for Reversing Character-Set Simplification and Abbreviation in Medieval Text
arXiv:2607.09291v1 Announce Type: new Abstract: Medieval document transcribers have very different practices; on top of that, heterogeneous digitization policies have resulted in corpora where the character-set must be viewed as fluid. In this paper we address the problem of changing between character-sets in a flexible manner. We focus on one-to-one character mappings and train characterlevel one-to-one RNNs to undo them with self-supervision; recovering half the CER even with 20 text lines. W
Creativity, honesty and designed forgetting emerge in small hyperbolic language models
arXiv:2607.09306v1 Announce Type: new Abstract: Language models are optimised for scale, yet remain functional rather than companionable, and as an assistant personalises into a companion, accumulating memory of one user, it quietly becomes someone, and can silently acquire traits that harm that user. What a companion is becoming, and what would make it worth becoming, has no reliable instrument: trained human raters cannot agree on the answer (Fleiss kappa = 0.074). Here we show that three sma
Automatic Thematic Indexing of Large Literary Corpora: A Machine Learning Approach to Voltaire's Complete Works
arXiv:2607.09316v1 Announce Type: new Abstract: Thematic indexing -- the practice of assigning structured conceptual labels to sections of text -- is essential to scholarly access in large-scale literary and historical editions, yet it remains a largely manual, labour-intensive process. This paper explores the application of machine learning to automatic thematic indexing, using two substantial sub-corpora of the Complete Works of Voltaire as a test case: the Essai sur les m\oe urs et l'esprit
Letting the Data Speak: Extracting Keywords from Crowdsourced Collections with AI
arXiv:2607.09324v1 Announce Type: new Abstract: Identifying and assigning keywords at scale is a technical, practical, and ethical challenge for crowdsourced collections. This article reports the findings of the "Extracting Keywords from Crowdsourced Collections" project, which used the Their Finest Hour Online Archive, a crowdsourced Second World War digital collection hosted by the University of Oxford, as a case study. The project evaluated three Natural Language Processing approaches to aut
WILDTRACE: Benchmarking Natural Evidence Trails in Long-Context Reasoning
arXiv:2607.09328v1 Announce Type: new Abstract: Answering complex questions over long documents frequently requires integrating evidence that the source itself disperses naturally across distant passages. In an incident report, the operating condition, design flaw, and missed safety check that jointly explain a disaster may appear dozens of sections apart; in a novel, a character's true motive may surface only through scenes far removed from the moment it becomes relevant. This source-internal
Towards Detecting Inconsistencies in End-to-end Generated TODs
arXiv:2607.09338v1 Announce Type: new Abstract: Generative AI is profoundly transforming the core technologies behind conversational systems, shifting from component-based to end-to-end approaches. However, Large Language Models (LLMs) may still generate inconsistencies, a critical issue particularly in Task-Oriented Dialogues (TODs), where system responses must strictly adhere to information from a domain knowledge base (e.g., restaurants in a city). A single hallucination (e.g., suggesting a
Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented Generation
arXiv:2607.09349v1 Announce Type: new Abstract: Retrieval-augmented generation evaluation checks whether model claims are factually grounded in retrieved documents. It does not check whether retrieved evidence is attributed to the correct entity. A clinical RAG response can pass every automated check (zero hallucinations, near-perfect faithfulness, real citations) while presenting drug Y's clinical evidence as evidence about queried drug X. We term this deceptive grounding (DG): a failure inv
Self-Guided Test-Time Training for Long-Context LLMs
arXiv:2607.09415v1 Announce Type: new Abstract: Long-context processing has become increasingly important for large language models (LLMs), but simply extending the context window does not guarantee effective utilization of long inputs. As input length grows, accuracy often degrades, indicating that models still struggle to identify and use the evidence most relevant to a question. A promising way to improve long-context utilization is test-time training (TTT), which treats the test context as
A Sovereign, Open-Source Foundation Model for German and English
arXiv:2607.09424v1 Announce Type: new Abstract: We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation model for German and English. Its hybrid design activates only 3B of 30B parameters per token and keeps the inference cache near-constant as context grows, giving it a decisive throughput advantage over dense models for long-context, high-concurrency deployment. Pretrained on roughly 27 trillion tokens with deliberately up-weighted Ger
Test-Time Scaling for Small VLMs on Multilingual Visual MCQ
arXiv:2607.09438v1 Announce Type: new Abstract: Test-time scaling (TTS) reliably improves reasoning in large language models, but whether it transfers to small open vision-language models remains unclear. We examine this on EXAMS-V, a multilingual visual multiple-choice benchmark, comparing self-consistency, describe-then-reason with PRM-guided beam search, and two post-hoc selectors across Qwen2.5-VL-7B-Instruct and Qwen3.5-4B. What matters is the conditions under which TTS runs, not the searc
Normalisation-Based Likelihood Ratio Estimation for Forensic Authorship Verification
arXiv:2607.09501v1 Announce Type: new Abstract: Authorship verification (AV) is the task of determining whether two texts were written by the same author. In a forensic context, the strength of AV evidence can be quantified using likelihood ratios. Most AV methods are score-based and deriving well-calibrated likelihood ratios from these scores requires a separate calibration model. This, in turn, requires additional amounts of case-relevant data, which is often time-consuming to obtain and prep
FreyaTTS Technical Report
arXiv:2607.09530v1 Announce Type: new Abstract: We introduce Freya-TTS, a compact, tokenizer-free, Turkish-first text-to-speech model designed for highly reliable and efficient conversational synthesis. Freya-TTS is a 183.2M-parameter non-autoregressive conditional flow-matching Diffusion Transformer (DiT) that operates in the frozen continuous latent space of AudioVAE2 (16 kHz encode, 48 kHz decode), allowing the model to focus its capacity on text-to-latent mapping while inheriting high-quali
Conceptual Networks for Cross-Linguistic Idiomatic Expressions:A Feature-Based Graph Approach
arXiv:2607.09576v1 Announce Type: new Abstract: We present an interpretable network-based framework for representing idiomatic and figurative meaning across eight typologically diverse languages, totaling 160 conventional expressions, the large majority of which are idiomatic. Each expression is annotated with binary conceptual features (containment, concealment, emotional, social, etc.) derived from cognitive-linguistic theory, and pairwise Jaccard similarities define a weighted graph. Communi
Tokenizer Transplantation: Mitigating Autoregressive Collapse in Edge-Efficient Bengali ASR
arXiv:2607.09598v1 Announce Type: new Abstract: Lightweight speech recognition models are critical for edge deployment, yet highly optimized architectures like Moonshine often fail on morphologically rich, non-Latin languages such as Bengali. This study identifies the root cause of this failure as the model's English-centric byte-level tokenizer, which fragments Bengali words into high-fertility byte chains and triggers catastrophic autoregressive collapse during inference. To resolve this, a n
StereoSplat+: Feed-Forward Stereo Gaussian Splatting with Diffusion-Assisted Progressive Inference
arXiv:2607.08808v1 Announce Type: new Abstract: Recent advances in 3D Gaussian Splatting (3DGS) have enabled high-quality, render-ready scene representations for novel-view synthesis. However, most existing 3DGS pipelines rely on multi-view observations (or non-causal access to future frames) to achieve sufficient coverage, which is often unavailable in on-device robotics and AR settings where sensing is restricted to a single stereo rig. Recovering a high-quality 3DGS scene from one stereo obs
Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing
arXiv:2607.08839v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are typically designed under the assumption that all modalities available during training will also be accessible at inference. However, many real-world settings violate this assumption, requiring models to operate under a privileged modality setting, where auxiliary modalities are available only during training. While these modalities contain valuable information, existing MLLMs largely fail to leverage th
Secure-by-Disguise: A Systematic Evaluation of Image Disguising for Confidential Medical Image Modeling
arXiv:2607.08867v1 Announce Type: new Abstract: Cloud-based deep learning enables large-scale medical image analysis but raises significant privacy concerns when sensitive patient images are outsourced for model development. Image disguising has recently emerged as a promising privacy-enhancing technology (PET) that transforms images into visually unintelligible representations while preserving information for downstream learning. We established a unified framework to evaluate representative me
Decoupled Illumination Priors for Spatially Controllable Multi-View Indoor Scene Relighting
arXiv:2607.08879v1 Announce Type: new Abstract: Indoor scene relighting demands photorealism, precise spatial control, and strict multi-view consistency. While diffusion-based image editing models enable semantic lighting manipulation via text prompts, enforcing exact 3D light placement often disrupts their generative priors. We propose Lume-Palette, a progressive framework that leverages semantic lighting priors for spatially controllable multi-view indoor relighting. The approach decouples re
HAT Super-Resolution and a PARSeq+CLIP4STR Voting Ensemble for Extreme In-the-Wild License Plate Recognition
arXiv:2607.08896v1 Announce Type: new Abstract: We describe our entry to the ICIP 2026 Grand Challenge on Extreme In-the-Wild License Plate Super-Resolution (XLPSR), which scored 9.73 wECR on the public validation leaderboard. The system pairs a Hybrid Attention Transformer super-resolution (HAT) front-end with an ensemble of two scene-text recognisers (PARSeq-S and CLIP4STR-B) and a confidence-weighted character-voting scheme that abstains on uncertain positions. We treat XLPSR as a recognitio
Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images
arXiv:2607.08932v1 Announce Type: new Abstract: Figure-ground organization in the human visual system relies on several shape-based cues, including surroundedness, convexity, and symmetry. While these cues have been extensively studied using abstract stimuli, little is known about how they operate under natural conditions or how they arise from the statistics of natural scenes. Deep neural networks offer a promising path forward: a model that relies on the same figure-ground cues as humans woul
Beyond Topicality: A Conceptual Analysis of Societal Relevance and Its Application to Search Results and AI Responses
arXiv:2607.09264v1 Announce Type: new Abstract: This paper examines "societal relevance," a concept introduced by Haider and Sundin to address the limitations of traditional relevance models in web search. While topical and user relevance are foundational to information science, they are insufficient for managing harmful content such as misinformation or discrimination found on the uncontrolled web. This study investigates three analytical questions: the definition of societal relevance, its pr
From Raw IDs to Semantic Planning: How Recommender Systems Utilize Information at Scale
arXiv:2607.09540v1 Announce Type: new Abstract: The evolution of recommender systems can be explored by asking how they utilize information at scale. Throughout most of the historical period under consideration during the past two decades, industrial systems have relied on raw IDs, which are discrete, globally unique, and semantically opaque identifiers that enable exact lookup, logging, and item-specific memorization at scale. Over time, however, recommender systems have sought to utilize rich
All Explanations are Wrong, But Many Are Useful: Exploring the Rashomon Explanation Set with Large Language Models
arXiv:2607.09502v1 Announce Type: cross Abstract: Explaining machine-learning models is increasingly important for decision-making and consumer trust, yet it is widely believed to come at a cost: existing Explainable AI (XAI) methods suffer from a persistent accuracy-explainability trade-off. We argue that this trade-off is not fundamental, but an artifact of treating explanation and prediction as separate objectives; when properly coupled, they become complementary, so that equipping a model t
Cross-media Scientific Research Achievements Query based on Ranking Learning
arXiv:2204.12121v2 Announce Type: replace Abstract: With the advent of the information age, the scale of data on the Internet is getting larger and larger, and it is full of text, images, videos, and other information. Different from social media data and news data, scientific research achievement information has the characteristics of many proper nouns and strong ambiguity. The traditional single-mode query method based on keywords can no longer meet the needs of scientific researchers and man
Do Recommendation Algorithms Work When Users Are LLM Agents? A Case Study on Moltbook
arXiv:2606.29762v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly populating web platforms, raising a fundamental question for recommender systems: do algorithms designed for human users still work when users are LLM agents that may not have well-defined content consumption preferences? We study this question by formulating a forum recommendation problem on Moltbook, a large-scale social media platform exclusively for autonomous AI agents running on the Open
Mining and searching association relation of scientific papers based on deep learning
arXiv:2204.11488v2 Announce Type: replace-cross Abstract: There is a complex correlation among the data of scientific papers. The phenomenon reveals the data characteristics, laws, and correlations contained in the data of scientific and technological papers in specific fields, which can realize the analysis of scientific and technological big data and help to design applications to serve scientific researchers. Therefore, the research on mining and searching the association relationship of sci
When to Repair a Graph ANN Index: A Matched-Budget Negative Result, and the Interpolated-Baseline Trap That Hid It
arXiv:2607.00728v2 Announce Type: replace-cross Abstract: Graph approximate-nearest-neighbor (ANN) indexes (HNSW, DiskANN/Vamana) lose recall under insert/delete churn, because deletions orphan the greedy-search paths that route through removed nodes. Production systems restore navigability by repairing the graph on a fixed schedule (consolidate every X operations). We asked whether triggering local edge repair on a measured navigability-degradation signal, rather than a blind clock, spends a f
EHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins
arXiv:2607.08793v1 Announce Type: new Abstract: Sepsis is a leading cause of mortality, yet optimal treatment policies remain contested. Existing reinforcement learning (RL) approaches learn fixed strategies for sepsis treatment, limiting adaptability to changing clinical objectives during inference. We propose EHRMPC, a framework that decouples learning patient dynamics from optimizing treatment by training a patient digital twin in the form of a generative electronic health record (EHR) model
Influence Diagnostics in High-dimensional M-estimation: Precise Asymptotics
arXiv:2607.09250v1 Announce Type: new Abstract: The impact of a given training point on a statistical model is classically measured through its leave-one-out influence, which quantifies the effect of its removal from the training set on the model accuracy. While the statistics of leave-one-out influences are well understood in the low-dimensional, large sample limit $n\to \infty, d=O(1)$, they become more intricate in high dimensions, as the influence of a given sample develops non-trivial depe
Spectrally Deconfounded Gradient Boosting
arXiv:2607.09371v1 Announce Type: new Abstract: Flexible machine-learning methods can be sensitive to hidden confounding: they may learn associations induced by unobserved confounders rather than stable signals. Spectral deconfounding mitigates this problem by shrinking high-variance directions of the covariate matrix that, under dense confounding, carry latent confounder information. Existing work has largely focused on linear models. We develop a nonlinear spectral deconfounding framework for
Deep Gaussian Processes on Directed Acyclic Graphs
arXiv:2607.09645v1 Announce Type: new Abstract: Many real-world processes can be represented as compositions of functions along a directed acyclic graph (DAG). In causal modelling, these correspond to the underlying mechanisms; in engineering, to multiple fidelity levels; and in gene-regulatory networks, to transcription factors. These functions are partially observed across the DAG, with noisy and heterogeneously sampled measurements, posing significant challenges for reconstruction, uncertain
Adaptive Bayes exactly tracks information over intrinsic time
arXiv:2607.08789v1 Announce Type: cross Abstract: Bayesian and multiplicative-weights updates reweight experts, models, or actions from sequential feedback. We show that the regret of any such update obeys an exact information-accounting identity. On each round, the learner's excess loss to any chosen comparator is the sum of an immediate payment for the uncertainty exposed by the round and a reduction in the information distance from the learner's current weights to the comparator. The cumulat
A Statistical Test for the Benefits of Personalizing Interventions
arXiv:2607.08951v1 Announce Type: cross Abstract: From medicine to marketing to social sciences, the promise of tailoring interventions to individuals is undeniable. However, practical applications force weighing personalization's potential benefits with its possible increased cost and fragility. We introduce a statistical hypothesis test that evaluates, given historical data, evidence that a personalized intervention policy's performance will surpass deploying the best single intervention. The
Nonconvex Composite Functional Constraints via First-Order Augmented Lagrangian Methods under Local Regularity
arXiv:2607.08954v1 Announce Type: cross Abstract: We study nonasymptotic convergence of primal-dual methods for a class of nonconvex constrained optimization problems with a convex-composite structure. In this class, both the objective and the functional inequality constraints are given by convex Lipschitz outer functions composed with smooth nonlinear inner mappings. The analysis is complicated by constraint violation in a nonconvex functional inequality system and by the lack of an a priori b
Stochastic Linear Bandits with Partially Observed Actions
arXiv:2607.08971v1 Announce Type: cross Abstract: The stochastic linear bandit, where actions are represented as vectors and rewards are linear, is a central paradigm for sequential decision making. We study a partially observed variant of this problem in which the learning agent only sees a random subset of coordinates for each action. Such partial observability arises naturally in settings like recommendation and healthcare, where full action descriptions can be expensive or even impossible t
Optimal Top-$k$ Identification from Pairwise Comparisons
arXiv:2607.08979v1 Announce Type: cross Abstract: We study the active learning problem of fixed-confidence top-$k$ identification from noisy pairwise comparisons. In this problem, an algorithm sequentially chooses pairs of items to compare, observes the outcomes, and stops when it can return the set of top-$k$ items with error probability at most $\delta$. The objective is to design such a $\delta$-correct procedure that minimizes the expected number of comparisons (the sample complexity). This
Achieving Almost Exact Recovery in Almost Quadratic Time: Rank-Based Graph Matching via Local Tree Correlation Tests
arXiv:2607.09087v1 Announce Type: cross Abstract: This paper studies graph matching under the correlated $\text{Erd\H{o}s-R\'{e}nyi}$ (ER) graph pair model. This model first samples an $\mathrm{ER}(n,\frac{\lambda}{ns})$ base graph, whose edges are then independently subsampled twice with probability $s$ to produce two correlated $\mathrm{ER}(n,\frac{\lambda}{n})$ graphs. We propose a graph matching algorithm that has $n^{2+o(1)}$ time complexity and achieves almost exact recovery with high pro
Solving Stochastic Fixed-Point Equations with High Probability
arXiv:2607.09097v1 Announce Type: cross Abstract: We study stochastic fixed-point equations $\mathbf{T}(\mathbf{x}) = \mathbf{x}$ over normed spaces $(\mathcal{E}, \|\cdot\|)$, where the operator $\mathbf{T}$ is nonexpansive or contractive and is accessed only through unbiased stochastic evaluations with bounded second central moment. Given $\epsilon > 0, \delta \in (0, 1)$, the goal is to output $\mathbf{x} \in \mathcal{E}$ such that $\|\mathbf{T}(\mathbf{x}) - \mathbf{x}\| \leq \epsilon$ with
Similarity search generalisation in contrastive learning with InfoNCE loss
arXiv:2607.09405v1 Announce Type: cross Abstract: Similarity search is a primary application of embedding models trained by contrastive learning. For one of the most popular contrastive learning loss functions, InfoNCE, we show that the population risk with $k$ negative samples is $O(1/k)$ close to an expected cross-entropy which quantifies deviation between i) a softmax similarity search over unseen data using the learned embedding function, and ii) an idealised softmax search over the same da
comprisk: A scikit-learn-compatible Python toolkit for competing-risks survival analysis
arXiv:2607.09431v1 Announce Type: cross Abstract: Medical time-to-event data are frequently subject to competing risks, where the occurrence of one terminal event precludes the others and standard survival methods that treat competing events as censoring yield biased absolute-risk estimates. Correct analysis instead targets the cause-specific cumulative incidence function (CIF). This methodology has been available to applied researchers almost exclusively through R packages, forcing Python-base
Near-optimal node-private community estimation in polynomial-time
arXiv:2607.09441v1 Announce Type: cross Abstract: In this paper, we resolve an open question of Klopp & Zadik (2026) by providing a high-probability polynomial-time, node-private algorithm which nearly matches the performance of their exponential-time node-private algorithm for exact recovery in stochastic block models. Our result involves an explicitly constructed Lipschitz surrogate for the penalized likelihood function, as well as a carefully devised accept-reject algorithm that samples comm
Deep Learning for Dynamic Programming with Recursive Utility Using First-order Conditions
arXiv:2607.09461v1 Announce Type: cross Abstract: This paper proposes the certainty-equivalent first-order learning (CEFOL) algorithm, a deep learning algorithm for solving discrete-time dynamic programming problems with recursive utility. Dynamic programming with recursive utility is challenging because nonlinear certainty equivalent appears in the Bellman equation and the first-order optimality conditions but is difficult to evaluate. By introducing a separate neural network to represent the
Neural Collapse Is Forbidden: Information Floors in Language Models
arXiv:2607.09487v1 Announce Type: cross Abstract: Within-class variance in language-model representations is commonly read as incomplete neural collapse. We argue it is allocated information storage, and that the allocation obeys a law. A one-line centering identity voids a family of simplex equiangular-tight-frame claims, including our own earlier ones; in dimensionless variance shares across 14 models, macro-category structure carries only 4-12% of representational variance and within-token c
High-Dimensional Interpolators Can Be Fragile: Heavy Tails and High-Dimensional Large Deviations
arXiv:2607.09547v1 Announce Type: cross Abstract: High-dimensional interpolation is common in modern machine learning, but its tail risk is less understood than its expected prediction risk. Existing theory shows that interpolating models can perform well in expectation, yet such guarantees do not determine the probability of rare, severe errors. In operations research and stochastic decision-making applications, rare estimation errors can have disproportionate downstream effects, so tail behav
A censoring-aware target interface for tabular foundation models in survival prediction
arXiv:2607.09577v1 Announce Type: cross Abstract: Time-to-event prediction from tabular patient data is central to prognosis and biomedical decision support, but right-censored follow-up prevents direct use of ordinary regression labels. Tabular foundation models offer reusable prediction machinery for modest heterogeneous datasets, yet they generally assume fully observed outcomes. We introduce SurvFM-RMST, a censoring-aware target-interface framework that converts survival outcomes into jackk
Dynamic Frechet Regression with Feature Selection for Distributional Data
arXiv:2607.09613v1 Announce Type: cross Abstract: Many scientific and engineering applications generate responses that are not scalars or vectors, but statistical objects whose form evolves over an ordered index such as time, depth. Probability distributions are a prominent example, capturing variability and uncertainty that cannot be summarized by low-dimensional statistics. When such responses are observed sequentially, the resulting dynamic distributional trajectories pose significant challe
Contrastive Learning on Multimodal Analysis of Electronic Health Records
arXiv:2403.14926v3 Announce Type: replace Abstract: Electronic health record (EHR) systems capture a wealth of multimodal clinical data, encompassing both structured clinical codes and unstructured clinical notes. Yet, many EHR-focused studies have traditionally examined these modalities in isolation or combined them using simplistic methods, overlooking the intrinsic synergy between them. In reality, these modalities are deeply interconnected, each containing clinically relevant and complement
Shared Selective Persistent Memory for Agentic LLM Systems
arXiv:2607.09493v1 Announce Type: new Abstract: Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive. Naively persisting entire conversation histories is token-inefficient and counterproductive: irrelevant context degrades generation quality. We introduce shared selective persistent m
Beyond Fixed Representations: The Vocabulary and Verifier Gaps in Open-Ended AI
arXiv:2607.09560v1 Announce Type: new Abstract: Modern AI systems are increasingly being evaluated for their ability to reason, code, prove theorems, use tools, and long-horizon research tasks. These are powerful capabilities, but they share a structural limitation: the representational frame within which the model operates, including its conceptual vocabulary, the space of admissible solutions it can search, and the criteria by which success is evaluated, is typically fixed and supplied in adv
TrustX Agent Risk Classification Framework (ARC): Risk-Tiering Internally Created Agentic AI Systems
arXiv:2607.09586v1 Announce Type: new Abstract: The proliferation of agentic AI systems across enterprise and public-sector contexts has outpaced the capacity of general-purpose AI risk frameworks to classify and govern them. In this paper, we introduce the TrustX Agent Risk Classification Framework, a structured, repeatable instrument that can be applied to seven types of agentic AI systems and is grounded in foundational pre-existing AI governance frameworks. At the core of the framework is a
Agora: Enhancing LLM Agent Reasoning Via Auction-Based Task Allocation
arXiv:2607.09600v1 Announce Type: new Abstract: Enhancing the reasoning capabilities of large language model (LLM) agents requires effective orchestration of diverse expert models and tools. However, existing frameworks typically call APIs based on coarse-grained matching between tasks and the functions of expert models or tools, while overlooking critical factors such as performance variability and cost efficiency among functionally similar alternatives. To address this, we propose Agora, a fr
ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI
arXiv:2607.09649v1 Announce Type: new Abstract: Concept-based explainable artificial intelligence (AI) can make model reasoning more human-understandable, but concept-level outputs are not automatically trustworthy. We introduce ConceptSMILE, a model-agnostic perturbation-based auditing framework for evaluating the reliability of concept-based explanations. Rather than replacing SMILE, ConceptSMILE extends its perturbation-based logic from feature- or region-level attribution to the auditing of
Minimal Decision Dynamics and Contextual Probability: A Quantum Tug-of-War Model
arXiv:2601.10034v2 Announce Type: cross Abstract: Decision making often exhibits context dependence that challenges classical probability theory. This paper develops a quantum-like extension of the Tug-of-War (QTOW) decision-making model to clarify when such context dependence can be represented by a single minimal internal state. The QTOW construction uses a qutrit internal state, conservation-preserving updates, and measurement-induced disturbance to model decision, learning, and probing oper
REFORGE: A Method for Benchmarking LLMs' Reverse Engineering Capabilities in Decompiled Binary Function Naming
arXiv:2607.07738v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to reverse-engineering tasks, and recent threat-intelligence reporting shows them operating inside live offensive-security workflows. Claims about their capability, however, outpace our ability to measure it. Existing benchmarks for LLM-assisted binary analysis treat the construction of function-level ground truth as a solved pre-processing step and report accuracy without disclosing how many
A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions
arXiv:2607.08776v1 Announce Type: cross Abstract: Despite the success of knowledge distillation (KD) in Large Language Models (LLMs), the underlying mechanism behind its efficacy remains unclear. In this paper, we propose a unified approach to explore the common mechanism of various KD methods using interactions. Specifically, we decompose the output score of the LLM into the sum of numerous interactions. Each interaction represents a nonlinear relationship involving a set of input variables (e
iLENS: Interpretable LLM-Guided Mixture-of-Experts for Neuroimaging Survival Analysis
arXiv:2607.08778v1 Announce Type: cross Abstract: Alzheimer's Disease (AD) is a complex neurodegenerative disorder that continues to impact millions of people worldwide. Predicting AD conversion during the prodromal stage remains critical for disease understanding and patient care. As such, survival models are widely used for AD risk prediction, yet they are typically static predictors with limited interpretability and no capacity for natural language reasoning. In this work, we propose iLENS,
Signed Symmetric Quantization for Few-Bit Integers
arXiv:2607.08779v1 Announce Type: cross Abstract: The signed integer alphabet contains one more negative representable value than positive. Yet, by convention, the standard symmetric integer quantizer fixes its scale to be strictly positive, which assigns this extra representable value to the negative tail and can force clipping of positive outliers. In this work, we show that, at few-bit precision, such clipping is a non-trivial source of quantization error. Asymmetric quantization addresses t
Sticky Routing: Training MoE Models for Memory-Efficient Inference
arXiv:2607.08780v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models activate only a sparse subset of experts per token, yet consecutive tokens frequently activate different experts -- causing constant weight swapping between slow storage and fast memory on edge devices. Existing remedies are either system-level (caching heuristics) or post-hoc (router fine-tuning), leaving the root cause unchanged during pretraining. We propose StickyMoE, a differentiable routing consistency loss
Reward Transport: Property Control in Flow Matching via Noise-Space Alignment
arXiv:2607.08781v1 Announce Type: cross Abstract: The coupling in flow matching -- the rule pairing noise vectors with data points -- is typically treated as a computational choice. We show that this coupling can instead serve as an alignment interface: by matching noise and data according to a target molecular property, it embeds controllable structure directly into the learned flow field. Building on this view, we introduce Reward Transport, which uses optimal transport coupling at training t
Director: Accelerating Distributed MoE Serving via Online Proactive Expert Placement
arXiv:2607.08782v1 Announce Type: cross Abstract: Expert parallelism has become the prevailing paradigm to serve Mixture-of-Experts (MoE) models. Its efficiency depends on the communication and computation latencies of the GPUs, which are linked to the placement of experts in the GPUs. Existing works for optimizing expert placement focus on leveraging past requests' expert activation patterns. However, they demonstrate deficiencies facing diverse and rapidly changing request patterns, calling f
LieBN: Batch Normalization over Lie Groups
arXiv:2607.08783v1 Announce Type: cross Abstract: Manifold-valued measurements are prevalent in various machine learning tasks. Recent advances have extended Deep Neural Networks (DNNs) to operate on manifolds, accompanied by normalization techniques tailored to different geometries, collectively referred to as Riemannian normalization. However, most existing Riemannian normalization methods are either designed for specific manifolds or fail to effectively normalize manifold-valued sample distr
HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning
arXiv:2607.08784v1 Announce Type: cross Abstract: Federated continual learning (FCL) evaluates how distributed clients learn from changing data streams while retaining previously learned knowledge. Existing evaluations are difficult to compare because they often change datasets, task splits, client data splits, task orders, backbones, memory assumptions, and reporting rules simultaneously. We introduce \textbf{HERO}, a heterogeneity-aware benchmark library for FCL. HERO builds benchmark streams
DaDaDa: A Dataset for Data Pricing in Data Marketplaces
arXiv:2607.08785v1 Announce Type: cross Abstract: High-quality data drives machine learning advances across industries. Recognizing the value of data, data transactions are increasingly common, giving rise to many data marketplaces, e.g., AWS Marketplace, Databricks, and Datarade. However, determining the appropriate prices for data products remains a significant challenge due to the unique properties of data products. Traditional pricing methods in economics can be categorized into the cost ap
Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices
arXiv:2607.08786v1 Announce Type: cross Abstract: With the growing deployment of large language models (LLMs), LLM inference cost has become a key challenge. Pruning techniques that introduce sparsity into weight matrices can accelerate inference. However, maintaining model quality typically limits pruning to moderate unstructured sparsity (around 50\%). At these sparsity levels, none of the existing GPU kernels for sparse matrix multiplication (SpMM) can outperform their dense counterparts. Th
LLM-Driven Evolutionary Generation of Multi-Objective Bayesian Optimization Algorithms
arXiv:2607.08791v1 Announce Type: cross Abstract: Designing effective multi-objective Bayesian optimization (MOBO) algorithms requires balancing many interdependent design choices whose optimal configuration is problem-dependent and typically demands deep expertise. We extend the LLaMEA framework to MOBO, using large language models as mutation and crossover operators within evolutionary strategies to generate complete algorithm implementations, with SMAC hyperparameter optimization integrated
Multi-Conditioned Diffusion Synthesis of Sand Boils for Low-Resource Earthen-Levee Inspection
arXiv:2607.08794v1 Announce Type: cross Abstract: Sand boils on earthen levees are safety-critical defects, but pixel-level detection is limited by scarce annotations. We present a diffusion-based synthesis pipeline for low-resource sand-boil imagery. Using Stable Diffusion XL fine-tuned with DreamBooth and conditioned by a multi-branch ControlNet stack, the pipeline generates synthetic inspection images from a small curated reference set. A soft-mask inpainting protocol preserves the real defe
TheBioCollection: Unified Pre-Training Scale LLM Corpus for Biology
arXiv:2607.08803v1 Announce Type: cross Abstract: The push toward large language models for biology (BioLM) has created a need for training corpora that can endow models with a genuine understanding of biology. However, existing biological resources, such as molecular databases, protein repositories, genomic annotations, single-cell atlases, and pathway databases, are scattered across heterogeneous formats and remain unorganized into a cohesive corpus for language model training. We present The
Toward Real-Time Sentence-Level Sign Language Translation
arXiv:2607.09611v1 Announce Type: new Abstract: Most sign language understanding systems operate at the level of isolated signs, limiting their usefulness in natural communication. We study sentence-level sign language translation (SLT) with the primary goal of real-time deployment rather than proposing a new translation architecture. We fine-tune a SHuBERT-ByT5 translation stack on a uniformly sampled 9,872-example subset of How2Sign, selected because of compute and storage constraints, using
Task-Specific Multimodal Question Answering Agents via Confidence Calibration and Incremental Reasoning for QANTA 2026
arXiv:2607.09623v1 Announce Type: new Abstract: We present our submission to the QANTA 2026 shared challenge at the ICML 2026 Workshop on Efficient Multimodal Question Answering (EMM-QA). Quanta evaluates multimodal quizbowl systems that answer pyramid-style questions from incrementally revealed text and accompanying images while operating under realistic efficiency constraints. The challenge consists of two distinct tasks: Tossup questions, which require deciding when to answer under uncertain
Sensitivity-Aware Thresholding and Token Routing for Activation Sparsification in Large Language Models
arXiv:2607.08991v1 Announce Type: cross Abstract: Efficient inference in Large Language Models (LLMs) requires deciding where computation can be reduced while preserving model quality. We study this problem through multilayer perceptron (MLP) activation sparsification and token-level conditional routing. We first propose Sensitivity-Aware Thresholding for Sparsity (SATS), a threshold calibration method to choose layerwise gate thresholds using a local MLP output sensitivity proxy rather than ca
Phone Segmentation and Recognition through Phonological Activation Mapping
arXiv:2607.09020v1 Announce Type: cross Abstract: Phone segmentation and recognition are inherently related tasks, yet modern approaches typically model them separately. We argue that phonetic structure is already latent in the representations of self-supervised speech models (S3Ms), and one only needs to steer them to solve both tasks. We leverage S3M-based Phonological Activation Mapping (SPAM), which maps each S3M representation frame to a vector of phonological feature activations, such as
VTaMo: Video-Text Alignment Model for Sign Language Translation
arXiv:2607.09126v1 Announce Type: cross Abstract: Sign language translation (SLT) converts continuous sign videos into spoken language text. Gloss-free approaches leverage pre-trained visual encoders and language models but rely on implicit cross-modal alignment from translation supervision alone. We present VTaMo, a framework that introduces explicit multi-granularity alignment at three levels: (1) local alignment via entropy-regularized optimal transport with a learnable null token for fine-g
Git-Assistant: Planning-Based Support for Updating Git Repositories
arXiv:2607.09224v1 Announce Type: cross Abstract: Version control systems are essential for collaborative software development, yet tools like git remain challenging for many practitioners. Recent advances in Large Language Models (LLMs) offer promising capabilities for interpreting developer intent, but their effectiveness in repository management tasks is limited by the need for formal reasoning. This work introduces Git-Assistant, an AI-based assistant that combines LLMs with automated plann
Super-Tuning: From Activation-Aware Pruning to Sparse Fine-Tuning
arXiv:2607.09287v1 Announce Type: cross Abstract: Large language models (LLMs) remain expensive to fine-tune because full-parameter updates require substantial memory, compute, and per-task storage. We study whether saliency signals originally developed for pruning can be reused to choose where a model should adapt. We propose Super, a sparse parameter-efficient fine-tuning (PEFT) method that fixes a small trainable support using a Wanda-style activation-weighted magnitude score [Sun et al., 20
Mach-Mind-4-Flash Technical Report
arXiv:2607.09375v1 Announce Type: cross Abstract: We present Mach-Mind-4-Flash, a 35B-parameter Mixture-of-Experts (MoE) agentic model with 3B activated parameters. Through post-training optimization alone without scaling pre-training compute, the model achieves performance on par with or surpassing that of 100B-parameter-class models. By introducing scalable agentic interaction environments for large-scale reinforcement learning, the model attains significant performance gains on real-world ap
Entity Alignment Method of Science and Technology Patent based on Graph Convolution Network and Information Fusion
arXiv:2311.00300v2 Announce Type: replace Abstract: The entity alignment of science and technology patents aims to link the equivalent entities in the knowledge graph of different science and technology patent data sources. Most entity alignment methods only use graph neural network to obtain the embedding of graph structure or use attribute text description to obtain semantic representation, ignoring the process of multi-information fusion in science and technology patents. In order to make us
Relation Extraction Model Based on Semantic Enhancement Mechanism
arXiv:2311.02564v2 Announce Type: replace Abstract: Relational extraction is one of the basic tasks related to information extraction in the field of natural language processing, and is an important link and core task in the fields of information extraction, natural language understanding, and information retrieval. None of the existing relation extraction methods can effectively solve the problem of triple overlap. The CasAug model proposed in this paper based on the CasRel framework combined
Topic model based on co-occurrence word networks for unbalanced short text datasets
arXiv:2311.02566v2 Announce Type: replace Abstract: We propose a straightforward solution for detecting scarce topics in unbalanced short-text datasets. Our approach, named CWUTM (Topic model based on co-occurrence word networks for unbalanced short text datasets), addresses the challenge of sparse and unbalanced short text topics by mitigating the effects of incidental word co-occurrence. This allows our model to prioritize the identification of scarce topics (low-frequency topics). Unlike pre
Accelerating Large Language Model Inference with Self-Supervised Early Exits
arXiv:2407.21082v3 Announce Type: replace Abstract: This paper presents a modular approach to accelerate inference in large language models (LLMs) by adding early exit heads at intermediate transformer layers. Each head is trained in a self-supervised manner to mimic the main model's predictions, allowing computation to stop early when a calibrated confidence threshold is reached. We evaluate several confidence metrics and show that entropy provides the most reliable separation between correct
Multi-Attribute Steering of Language Models via Targeted Intervention
arXiv:2502.12446v3 Announce Type: replace Abstract: Inference-time intervention (ITI) has emerged as a promising method for steering large language model (LLM) behavior in a particular direction (e.g., improving helpfulness) by intervening on token representations without costly updates to the LLM's parameters. However, existing ITI approaches fail to scale to multi-attribute settings with conflicts, such as enhancing helpfulness while also reducing toxicity. To address this, we introduce Multi
Beyond LLMs: A Linguistic Approach to Causal Graph Generation from Narrative Texts
arXiv:2504.07459v2 Announce Type: replace Abstract: We propose a novel framework for generating causal graphs from narrative texts, bridging high-level causality and detailed event-specific relationships. Our method first extracts concise, agent-centered vertices using large language model (LLM)-based summarization. We introduce an "Expert Index," comprising seven linguistically informed features, integrated into a Situation-Task-Action-Consequence (STAC) classification model. This hybrid syste
GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs
arXiv:2507.18043v2 Announce Type: replace Abstract: Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights. However, most existing approaches rely on fixed, global intervention vectors, overlook the causal influence of individual input tokens, and fail to leverage informative gradients from the model's logits, particularly in multim
Evaluating Retrieval-Augmented Generation vs. Long-Context Input for Clinical Reasoning over EHRs
arXiv:2508.14817v2 Announce Type: replace Abstract: Objective: To evaluate whether retrieval-augmented generation (RAG) can serve as an efficient alternative to long-context prompting for clinical reasoning over electronic health records (EHRs). Methods: We defined three EHR-based tasks that are replicable across health systems and vary in reasoning complexity: 1) extracting imaging procedures (modality, date, and anatomic site), 2) generating timelines of therapeutic antibiotic use, and 3) ide
REAL: REtrieval-reAsoning and Logic-constructed Attention Behaviors for Long-Context KV Cache Compression
arXiv:2508.15806v2 Announce Type: replace Abstract: The growing sequence length of large language models poses significant challenges for key-value (KV) caches. Existing state-of-the-art cache eviction methods primarily analyze the inference behavior of attention heads in successful retrieval-reasoning cases, often overlooking diverse behaviors in failure cases, such as bias and distraction. This oversight limits the potential to leverage heterogeneous head behaviors for improved eviction perfo
Decoupling Task-Solving and Output Formatting in LLM Generation
arXiv:2510.03595v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly adept at solving complex problems, such as mathematical reasoning and automatic evaluation. However, performance often degrades when prompts intertwine task instructions with rigid formatting requirements. This entanglement creates competing goals for the model, hindering its reasoning capabilities. To address this, we introduce Deco-G, a decoding framework that explicitly decouples format adherenc
Probabilistic Textual Time Series Depression Detection
arXiv:2511.04476v2 Announce Type: replace Abstract: Accurate and interpretable predictions of depression severity are essential for clinical decision support, yet existing models often lack uncertainty estimates and temporal interpretability. We propose PTTSD, a Probabilistic framework for Depression Detection from clinical interview utterance sequences that predicts PHQ-8 scores while modeling calibrated uncertainty. PTTSD includes sequence-to-sequence and sequence-to-one variants, both combin
Point of Order: Action-Aware LLM Persona Modeling for Data-Grounded Civic Deliberation
arXiv:2511.17813v3 Announce Type: replace Abstract: LLM-based simulations can enable controlled studies of civic deliberation, but current systems lack speaker-attributed data and methods for evaluating long-form institutional behavior. ASR transcripts typically use anonymous labels such as $Speaker\_1$, preventing models from learning stable participant behavior across meetings. We present a reproducible pipeline that converts public Zoom recordings into speaker-attributed transcripts enriched
Uncovering smooth structures in single-cell data with PCS-guided neighbor embeddings
arXiv:2506.22228v2 Announce Type: replace Abstract: Single-cell sequencing is revolutionizing biology by enabling detailed investigations of cell-state transitions. Many biological processes unfold along continuous trajectories, yet it remains challenging to extract smooth, low-dimensional representations from inherently noisy, high-dimensional single-cell data. Neighbor embedding (NE) algorithms, such as t-SNE and UMAP, are widely used to embed high-dimensional single-cell data into low dimens
Near-optimal Delta-convex Estimation of Lipschitz Functions
arXiv:2511.15615v2 Announce Type: replace Abstract: This paper presents a tractable algorithm for estimating an unknown Lipschitz function from noisy observations and establishes an upper bound on its convergence rate. The approach extends max-affine methods from convex shape-restricted regression to the more general Lipschitz setting. A key component is a nonlinear feature expansion that maps max-affine functions into a subclass of delta-convex functions, which act as universal approximators o
Global Sequential Testing for Multi-Stream Auditing
arXiv:2602.21479v3 Announce Type: replace Abstract: Across many risk-sensitive areas, it is critical to continuously audit machine learning systems as we receive more data to quickly determine if they are performing as designed. This auditing task can be modeled as a sequential hypothesis testing problem with $k$ data streams and a global null hypothesis that asserts the system operates as intended across all $k$ streams. Under the alternative, the standard global sequential test, which uses a
Tuning Derivatives for Causal Fairness in Machine Learning
arXiv:2605.05882v2 Announce Type: replace Abstract: Artificial-intelligence systems are becoming ubiquitous in society, yet their predictions typically inherit biases with respect to protected attributes such as race, gender, or age. Classical fairness notions, most notably Statistical Parity (SP), demand that predictions be independent of the protected attributes, but are overly restrictive when these attributes influence mediating variables that are considered business necessities. Recent cau
Kernel of Partition Paths: A Unified Representation for Tree Ensembles
arXiv:2606.18853v3 Announce Type: replace Abstract: A recent line of work has reframed individual decision trees as linear models on engineered features associated with their splits, opening routes for oracle inequalities and feature-importance reinterpretation, but leaving open the question of what unified geometric object a forest induces when one indexes its feature map by nodes rather than by splits. The present paper studies that object. KPP indexes the feature map by the nodes of the fore
Hierarchical Causal Models
arXiv:2401.05330v3 Announce Type: replace-cross Abstract: Causal questions often arise in settings where data are hierarchical: subunits are nested within units. Consider students in schools, cells in patients, or cities in states. In these settings, unit-level variables (e.g., a school's budget) may affect subunit-level outcomes (e.g., student test scores), and subunit-level characteristics may aggregate to influence unit-level outcomes. In this paper, we show how to analyze hierarchical data
Accelerated Fully First-Order Methods for Bilevel and Minimax Optimization
arXiv:2405.00914v4 Announce Type: replace-cross Abstract: We present in this paper novel accelerated fully first-order methods in \emph{Bilevel Optimization} (BLO). Firstly, for BLO under the assumption that the lower-level functions admit the typical strong convexity assumption, the \emph{(Perturbed) Restarted Accelerated Fully First-order methods for Bilevel Approximation} (\texttt{PRAF${}^2$BA}) algorithm leveraging \emph{fully} first-order oracles is proposed, whereas the algorithm for find
Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validation
arXiv:2506.03062v2 Announce Type: replace-cross Abstract: A/B tests in online experiments face statistical power challenges when testing multiple candidates simultaneously, while adaptive experimental designs (AED) alone fall short in inferring experiment statistics such as the average treatment effect, especially with many metrics (e.g., revenue, safety) and heterogeneous variances. This paper proposes a fixed-budget multi-metric AED framework with a two-phase structure: an adaptive exploratio
Cluster and then Embed: A Modular Approach for Visualization
arXiv:2509.03373v2 Announce Type: replace-cross Abstract: Dimensionality reduction methods such as t-SNE and UMAP are popular methods for visualizing data with a potential (latent) clustered structure. They are known to group data points at the same time as they embed them, resulting in visualizations with well-separated clusters that preserve local information well. However, t-SNE and UMAP also tend to distort the global geometry of the underlying data. We propose a more transparent modular ap
A Computable Measure of Suboptimality for Entropy-Regularised Variational Objectives
arXiv:2509.10393v4 Announce Type: replace-cross Abstract: Several methods in statistics and machine learning target a probability distribution for which an entropy-regularised variational objective is minimised. This increased flexibility introduces a computational challenge, as one loses access to an explicit unnormalised density for the target. To mitigate this difficulty, we introduce a novel measure of suboptimality called 'gradient discrepancy', and in particular a kernel gradient discrepa
Gradient-enhanced global sensitivity analysis with Poincar{\'e} chaos expansions
arXiv:2510.03056v2 Announce Type: replace-cross Abstract: Spectral methods, also known as chaos expansions, are widely used in global sensitivity analysis (GSA), as they leverage orthogonal bases of L2 spaces to efficiently compute Sobol' indices, particularly in data-scarce settings. When derivatives of the model are available, a desirable property, both for modeling and GSA purposes, is for the derivatives of the basis functions to also form an orthogonal basis. We demonstrate that the only b
How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy
arXiv:2512.03238v2 Announce Type: replace-cross Abstract: High quality data is needed to unlock the full potential of AI for end users. However finding new sources of such data is getting harder: most publicly-available human generated data will soon have been used. Additionally, publicly available data often is not representative of users of a particular system -- for example, a research speech dataset of contractors interacting with an AI assistant will likely be more homogeneous, well articu
Principles of Lipschitz continuity in neural networks
arXiv:2602.04078v2 Announce Type: replace-cross Abstract: Deep learning has achieved remarkable success across a wide range of domains, significantly expanding the frontiers of what is achievable in artificial intelligence. Yet, despite these advances, critical challenges remain -- most notably, ensuring robustness to small input perturbations and generalization to out-of-distribution data. These critical challenges underscore the need to understand the underlying fundamental principles that go
Upper-Linearizability of Online Non-Monotone DR-Submodular Maximization over Down-Closed Convex Sets
arXiv:2602.20578v2 Announce Type: replace-cross Abstract: We study online maximization of non-monotone Diminishing-Return(DR)-submodular functions over down-closed convex sets, a regime where existing projection-free online methods suffer from suboptimal regret and limited feedback guarantees. Our main contribution is a new structural result showing that this class is $1/e$-linearizable under carefully designed exponential reparametrization, scaling parameter, and surrogate potential, enabling
Machine Learning for Network Attacks Classification and Statistical Evaluation of Adversarial Learning Methodologies for Synthetic Data Generation
arXiv:2603.17717v4 Announce Type: replace-cross Abstract: Supervised detection of network attacks has always been a critical part of network intrusion detection systems (NIDS). Nowadays, in a pivotal time for artificial intelligence (AI), with even more sophisticated attacks that utilize advanced techniques, such as generative artificial intelligence (GenAI) and reinforcement learning, it has become a vital component if we wish to protect our personal data, which are scattered across the web. I
From Cross-Validation to SURE: Asymptotic Risk of Tuned Regularized Estimators
arXiv:2603.20388v2 Announce Type: replace-cross Abstract: We derive the asymptotic risk function of regularized empirical risk minimization (ERM) estimators tuned by $n$-fold cross-validation (CV). The out-of-sample prediction loss of such estimators converges in distribution to the squared-error loss (risk function) of shrinkage estimators in the normal means model, tuned by Stein's unbiased risk estimate (SURE). This risk function provides a more fine-grained picture of predictive performance
Bridging the Gap Between Climate Science and Machine Learning in Climate Model Emulation
arXiv:2603.22320v2 Announce Type: replace-cross Abstract: For decades, physics-based climate models have been used to provide insights for climate decision-making. Their application is, however, constrained by significant computational and technical demands. Machine learning (ML) emulators offer a way to reduce these high computational costs; yet, it remains challenging to use ML emulators effectively in climate research. In practice, climate scientists often bypass emulators altogether, and ma
Enhancing AI and Dynamical Subseasonal Forecasts with Probabilistic Bias Correction
arXiv:2604.16238v2 Announce Type: replace-cross Abstract: Decision-makers rely on weather forecasts to plant crops, manage wildfires, allocate water and energy, and prepare for weather extremes. Today, such forecasts enjoy unprecedented accuracy out to two weeks thanks to steady advances in physics-based dynamical models and data-driven artificial intelligence (AI) models. However, model skill drops precipitously at subseasonal timescales (2 - 6 weeks ahead), due to compounding errors, systemic
Prompt-Driven Exploration
arXiv:2607.08837v1 Announce Type: cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject stochasticity in the action space, but such jitter only yields rollouts close to the original. Escaping a weak policy often requires global perturbations that action noise cannot produce. Large language models (LLMs) and vision-language-action (VLA) models offer a pathway: they condition the policy on a na
A Novel Parallel QCNN Architecture with Efficient Classical Simulability
arXiv:2607.08928v1 Announce Type: cross Abstract: This work presents a study of an implementation of a novel Quantum Convolutional Neural Network (QCNN) for binary classification of images from the Modified National Institute of Standards and Technology (MNIST) dataset. Using a novel architecture inspired by previous QCNN and classical convolutional neural network (CNN) implementations, we use a hierarchical partitioning approach to implement a QCNN circuit that can be approximated and simulate
Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution
arXiv:2607.08960v1 Announce Type: cross Abstract: Warehouse operations are governed by Standard Operating Procedures (SOPs) that encode complex, multi-system decision logic, which must be executed reliably under strict time constraints, yet LLM agents lack mechanisms to enforce procedural compliance and degrade under the context overload full SOP specifications introduce. We present Eluna, a production-deployed agentic system for reliable SOP execution. Eluna is a graph-guided, multi-agent fram
NL-PAC: Specification Ambiguity and Certified Minimax Risk Floors in LLM-Mediated Supervision
arXiv:2607.08961v1 Announce Type: cross Abstract: Large language models increasingly provide labels, evaluations, and feedback for tasks specified in natural language. When a specification admits multiple readings but the supervision channel does not reveal which is operative, additional labels reduce sampling error without resolving the resulting identification problem. We introduce Natural Language PAC (NL-PAC), a framework that uses a fixed model's thresholded decoding law to define admissib
MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs
arXiv:2607.08970v1 Announce Type: cross Abstract: Recent benchmarks for VLMs largely assess single- or limited-view perception, leaving untested the core cognitive ability to integrate observations across viewpoints into a coherent, world-centric (allocentric) 3D mental model. We introduce MultiView-Bench, a diagnostic benchmark expressly designed to evaluate multi-view integration for holistic 3D scene comprehension. Unlike existing datasets that focus on pixel-level mapping or camera-relative
CLAP: Direct VLM-to-VLA Adaptation via Language-Action Grounding
arXiv:2607.08974v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) inherit semantic capabilities from pretrained VLMs, yet large-scale post-training on robot data and architectural modifications can reshape the backbone so extensively that it becomes difficult to isolate what the VLM contributes to control. Directly converting pretrained VLMs into VLAs with minimal architectural change offers a more transparent path to understanding how VLM capabilities transfer across model
The Patchwork Problem in LLM-Generated Code
arXiv:2607.08981v1 Announce Type: cross Abstract: LLM-generated code often compiles, passes tests, and appears correct, yet breaks once deployed. The root cause is frequently structural rather than logical. A generated endpoint references configuration keys never declared in the project, an import targets a package that does not exist in any registry, or a new route omits the authentication guard applied to every sibling endpoint. Each patch is locally valid but globally incoherent, and standar
AlphaZero in Sparsely Rewarded Games: Limits and Auxiliary Supervision
arXiv:2607.08984v1 Announce Type: cross Abstract: AlphaZero has demonstrated that a neural-guided Monte Carlo Tree Search can achieve superhuman performance, but strong play does not necessarily imply perfect play. We study this gap in two oracle-evaluable domains with contrasting structure: Connect Four, a solved partisan game with exact game-theoretic values, and Chomp, an impartial game whose optimal play is governed by Grundy-number structure. Under a unified self-play $+$ MCTS pipeline, we
Model Agnostic Graph Prompt Learning for Crystal Property Prediction
arXiv:2607.08996v1 Announce Type: cross Abstract: Graph Neural Networks have emerged as a powerful tool for the fast and accurate prediction of various crystal properties. These models often encode domain-specific knowledge into their graph encoding modules, which increases their parameter size and makes their performance heavily dependent on domain expertise. Added to this, explicitly incorporating all chemical and structural features, that might influence a specific crystal property into the
Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing
arXiv:2607.09015v1 Announce Type: cross Abstract: We study contextual bandit problems with correlated arms and access to surrogate reward signals produced by a machine learning model, motivated by applications such as large language model (LLM) routing. Unlike classical contextual bandits that rely solely on bandit feedback and assume conditional independence across arms, our setting allows context-dependent inter-arm correlations and auxiliary reward information that may be noisy or misspecifi
Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systems
arXiv:2607.09025v1 Announce Type: cross Abstract: Artificial intelligence (AI) is shifting scientific discovery from task-specific workflows towards autonomous systems that organize exploration with experimental and human feedback in open-ended candidate spaces. Evolutionary computation (EC) provides a computational basis for feedback-driven discovery because population-based search can maintain diverse scientific candidates while steering exploration through accumulated evidence. However, EC p
Quantum Logic as the Logic of Contexts
arXiv:2607.09032v1 Announce Type: cross Abstract: Quantum logic is usually presented as a non-classical departure from ordinary reasoning forced on us by quantum mechanics, with classical logic kept as the secure starting point. We argue for the opposite order of explanation in a finite and fully computable setting. The free orthomodular lattice on two generators has ninety-six elements, the direct product of a six-element non-distributive factor and a sixteen-element Boolean factor. Reading th
On Locality and Length Generalization in Visual Reasoning
arXiv:2607.09061v1 Announce Type: cross Abstract: A striking feature of the human visual system is that it ingests visual information through a series of local foveated glimpses, rather than a single global computation. This makes human vision distinctly different from most popular computer vision models in use today, which input images globally and in a single shot. A natural question therefore is whether local, sequential vision models may provide any fundamental computational benefits in add
Inside the Skill Market: From Software Engineering Activities to Reusable Agent Skills
arXiv:2607.09065v1 Announce Type: cross Abstract: Software engineering (abbrev. SE) has continuously evolved through increasingly powerful forms of reuse, from source code and libraries to components and services. Recent advances in AI agents have introduced a potentially new reusable artifact: skills. Emerging agent skill repositories and marketplaces enable developers to package, share, and reuse SE expertise as reusable skills. This trend raises a fundamental question: what SE activities are
A Coreset Selection Framework with Ensemble Aggregation for Image Classification
arXiv:2607.09100v1 Announce Type: cross Abstract: The rapid growth of image data has produced large-scale datasets, raising concerns about the time and memory costs of model training. Selecting representative training subsets, however, remains challenging: individual sample contributions are unclear, and model behavior varies across datasets and runs. We address these challenges with a framework that combines coreset selection with an ensemble aggregation over multiple runs. For coreset selecti
Beyond Metadata: CAPRA for Hidden Subgroup Analysis under Missing Metadata in Medical Imaging
arXiv:2607.09102v1 Announce Type: cross Abstract: Medical imaging models are often deployed without the demographic, acquisition, and quality metadata needed for subgroup auditing. Once those metadata disappear, clinically critical failure modes can be masked by strong aggregate performance, and many robust-learning methods lose the group structure they rely on. We present CAPRA, a calibrated proxy-axis framework for hidden subgroup analysis under missing metadata. CAPRA predicts image-derived
Event Stream based Multi-Modal Video Anomaly Detection: A Benchmark Dataset and Algorithms
arXiv:2607.09114v1 Announce Type: cross Abstract: Video anomaly detection (VAD) is critical for automated surveillance but remains fragile under challenging conditions such as illumination variations, fast motion, and complex backgrounds when relying solely on visible light videos. To address these limitations, we propose EVAD, an event enhanced VAD framework that jointly exploits conventional video and event streams captured by bio inspired event cameras. Event sensors asynchronously capture b
IB-Flow: Information Bottleneck-Guided CFG Distillation for Few-Step Text-to-Image Generation
arXiv:2607.09133v1 Announce Type: cross Abstract: While large-scale text-to-image generative models have achieved unprecedented visual performance, their inherent reliance on multi-step iterative solvers incurs severe inference latency. Few-step distillation targeting the Classifier-Free Guidance (CFG) trajectory has emerged as the prevalent dual-dimensional compression paradigm. However, existing frameworks remain subjugated by a coarse-grained blind injection paradigm that perpetually enforce
A Personalized Computational Framework for Assessing the Sufficiency of Partially Observed Data in Healthcare AI models
arXiv:2607.09165v1 Announce Type: cross Abstract: Achieving early and timely diagnosis and treatment for disease is a major challenge. Recent applications of machine learning (ML) algorithms trained on patient data have shown promise in many different settings for predicting the patient health state. A challenge often faced when applying these ML algorithms is that at any given time, not all clinical variables (features) needed as input to perform prediction tasks are available. We define the c
Attention to Detail: Evaluating Energy, Performance, and Accuracy Trade-offs Across vLLM Configurations
arXiv:2607.09172v1 Announce Type: cross Abstract: Large Language Models are reshaping how software is developed and maintained. They are typically deployed in production using inference engines such as vLLM, which can efficiently serve pre-trained, highly configurable models. While prior work has focused on model architectures and hardware acceleration, the impact of inference engine configuration on energy consumption, performance, and output quality remains poorly understood. In this paper,
DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data
arXiv:2607.09348v1 Announce Type: new Abstract: Causal discovery from unstructured data is a challenging yet underexplored task in high-expertise domains such as healthcare, finance, and education. Existing methods typically leverage the general knowledge of large language models (LLMs) to identify causal factors from unstructured data and annotate them into structured data for causal graph construction. However, they remain limited by two key challenges (CHs): (CH1) insufficient identification
AugServe: Adaptive Request Scheduling for Augmented Large Language Model Inference Serving
arXiv:2512.04013v3 Announce Type: replace Abstract: As augmented large language models (LLMs) with external tools become increasingly popular in web applications, improving augmented LLM inference serving efficiency and optimizing service-level objectives (SLOs) are critical for enhancing user experience. To achieve this, inference systems must maximize request handling within latency constraints, referred to as increasing effective throughput. However, existing systems face two major challenge
Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens
arXiv:2602.10229v2 Announce Type: replace Abstract: While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it constrains the model's thoughts to a discrete vocabulary space. Recently, reasoning in continuous latent space has emerged as a promising alternative, but current paradigms suffer from feature collapse and instability due to distribution mismatch when recurrently reusing hidden states, or alignment issues when relying on assistant m
QQ: A Language Metadata Toolkit for Multilingual NLP
arXiv:2603.00620v2 Announce Type: replace Abstract: Multilingual NLP research increasingly involves hundreds or thousands of languages across different datasets. Managing, discovering, and reporting language metadata becomes a common hurdle at these scales. We present QQ, a metadata toolkit and browser explorer. QQ compiles language metadata sources into a graph of language varieties, scripts, regions, identifiers, names, and relations, and exposes it through a Python API, a command-line interf
Lost in Backpropagation: The LM Head is a Gradient Bottleneck
arXiv:2603.10145v2 Announce Type: replace Abstract: The last layer of neural language models (LMs) projects output features of dimension $D$ to logits in dimension $V$, the size of the vocabulary, where usually $D \ll V$. This mismatch is known to raise risks of limited expressivity in neural LMs, creating a so-called softmax bottleneck. We show the softmax bottleneck is not only an expressivity bottleneck but also an optimization bottleneck. Backpropagating $V$-dimensional gradients through a
Hierarchical Chain-of-Thought: Enhancing LLM Reasoning Performance and Efficiency
arXiv:2604.00130v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting has significantly improved the reasoning capabilities of large language models (LLMs). However, conventional CoT often relies on unstructured, flat reasoning chains that suffer from redundancy and suboptimal performance. In this work, we introduce Hierarchical Chain-of-Thought (Hi-CoT), a structured reasoning paradigm specifically designed to address the challenges of complex, multi-step reasoning. Hi-CoT decom
RELISH: LLM REgression with a Latent Iterative State Head
arXiv:2604.01206v2 Announce Type: replace Abstract: We present RELISH (REgression with a Latent Iterative State Head), a novel, lightweight architecture designed for text regression with large language models. Rather than decoding numeric targets as text or aggregating multiple generated outputs, RELISH predicts scalar values directly from frozen LLM representations by iteratively refining a learned latent state through cross-attention over token-level representations, and then mapping the fina
SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation
arXiv:2604.22294v2 Announce Type: replace Abstract: Systematic reviews -- which requires comprehensive evidence collection and synthesis from large document corpora in response to targeted research questions -- are foundational in finance, social sciences, and other technical fields. Manual construction of evidence tables is labor-intensive, and recent LLM-based assistants relying on embedding or keyword based search often fail to meet the coverage standards of systematic reviews. We introduce
Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistance
arXiv:2606.18613v3 Announce Type: replace Abstract: The most plausible near-term role of medical LLMs is to assist rather than replace physicians, yet current evaluations often test isolated capabilities: clinical knowledge, EHR system interaction, or patient communication. Physician assistance instead requires coordinating these capabilities within the same interaction, where physicians issue underspecified requests, patients describe symptoms ambiguously, and EHR systems demand precise tool u
Memory-Managed Long-Context Attention: Bounded Editable Memory with a Hard Lifecycle and Calibrated Sparse Fallback
arXiv:2606.28876v2 Announce Type: replace Abstract: We study memory-managed long-context attention: explicit bounded memory with a learned query-independent writer, lifecycle control, query-aware reading, calibrated sparse fallback, and frozen-LLM generation from raw evidence. Track A is a controlled versioned-variable task where last-mention retrieval is wrong by construction. Its full lifecycle scores 1.000 on all three seeds versus a 0.333 lexical baseline, and generation reaches 300/300 at
Smooth Scaling Laws Hide Stepwise Token Learning
arXiv:2606.29858v2 Announce Type: replace Abstract: Language model loss follows remarkably regular scaling laws over model and data size, yet it remains unclear why the aggregate loss should exhibit a power-law form. Existing explanations often attribute this regularity to a heavy-tailed spectrum of pattern difficulty in natural language, but this view has not been directly validated at token-level granularity in large-scale real-data training. We present a token-level framework that decomposes
Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors
arXiv:2505.14300v2 Announce Type: replace-cross Abstract: White-box monitoring is increasingly adopted as an auditing tool as Large Language Models (LLMs) are deployed in daily operations to ensure safe model behavior. However, white-box monitors can be circumvented, and the mechanisms underlying such evasion have not been systematically characterized, nor have principled defenses been proposed. This work addresses both challenges. Controlled red-team experiments reveal two primary evasion stra
Leveraging Multi-Agent System (MAS) and Fine-Tuned Small Language Models (SLMs) for Automated Telecom Network Troubleshooting
arXiv:2511.00651v2 Announce Type: replace-cross Abstract: Telecom networks are rapidly growing in scale and complexity, making effective management, operation, and optimization increasingly challenging. Although Artificial Intelligence (AI) has been applied to many telecom tasks, existing models are often narrow in scope, require large amounts of labeled data, and struggle to generalize across heterogeneous deployments. Consequently, network troubleshooting continues to rely heavily on Subject
Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue
arXiv:2605.12920v3 Announce Type: replace-cross Abstract: Effective collaboration between embodied agents requires more than acting in a shared environment; it demands communication grounded in each agent's evolving understanding of the world. When agents can only partially observe their surroundings, coordination without communication is provably hard, but communication can, in principle, bridge this gap by allowing agents to share observations and align their world models. In this work, we ex
Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation
arXiv:2605.14563v2 Announce Type: replace-cross Abstract: Automated code documentation is essential for modern software development, providing the contextual grounding that both human developers and coding agents rely on to navigate large codebases. Existing repository-level approaches process components independently, causing redundant retrieval and conflicting descriptions across documents while producing outputs that lack hierarchical structure. Therefore, we propose MemDocAgent, a long-hori
Explaining is Harder Than Predicting Alone: Evaluating Concept-based Explanations of MLLMs as ICL Visual Classifiers
arXiv:2605.28215v2 Announce Type: replace-cross Abstract: In-context learning (ICL) enables multimodal large language models (MLLMs) to classify images from a few labelled examples. Yet, how these models use the provided context remains opaque. While Chain-of-Thought prompting is widely used, recent work argues that it may not reflect true internal computation. In this paper, we systematically evaluate the concept-based explainability of frozen MLLMs under few-shot ICL using five conditions o
Generative Communications: Overview, Technologies, and Trends
arXiv:2607.09183v1 Announce Type: cross Abstract: The groundbreaking development of generative artificial intelligence (AI) is rapidly boosting the ability to generate content such as images and videos, reshaping communication paradigms. This article introduces generative communications (GenCom), a novel paradigm for 6G networks in which large AI models (LAMs) drive semantic understanding, reasoning, and content generation, embedding these into the communication process. Unlike traditional syst
Interference and Retention in Continual Learning
arXiv:2607.09202v1 Announce Type: cross Abstract: Continual learning commonly relies on post-hoc mechanisms such as replay, elastic regularization, or distillation. This work argues that forgetting should instead be modeled directly as interference between tasks. In the frozen-feature regime, forgetting from learning a new task is exactly the interference energy induced on the old task. In deep networks, the same quantity is recovered through path-averaged curvature with minimal additional forw
Tactile and Vision Conditioned Contact-Centric Control for Whole-Arm Manipulation
arXiv:2607.09218v1 Announce Type: cross Abstract: Whole-arm manipulation involves direct contact with the environment while the robot completes a task by distributing contact across multiple links as contacts form, slide, and break. This setting breaks common implicit assumptions in many learning-based manipulation pipelines: arm configuration tightly couples motion and contact forces, contact state is partially observed under occlusion, and purely learned rollouts can become physically inconsi
All you need is SAMPAT
arXiv:2607.09235v1 Announce Type: cross Abstract: The current state of the art in AI/ML rests on deep neural architectures, which, in general, suffer from a lack of interpretability. Interpretability is crucial to gleaning insights while analyzing experimental data, where quantitative predictions may not be adequate for a scientist. We present a three layer neural architecture, SAMPAT (Smooth Approximation via Multivariate Polynomials and Analytic Transformations), that can provably learn a con
LLMs for health: Perceived benefits, risks, intention to use AI chatbots, and willingness to self-disclose across sensitive health topics
arXiv:2607.09253v1 Announce Type: cross Abstract: AI chatbots are increasingly used for answering health-related questions. This study examines the role of topic type discussed with an AI chatbot and individual characteristics on perceived benefits and risks, intention to use an AI chatbot, and willingness to self-disclose health information. We conducted an online experiment with a 2 (topic type: physical versus psychological, between-subjects) x 2 (topic sensitivity: low versus high, within-s
Blockchain-Linked Auditable Decision Management for Telecom/IoT Fraud-Control Requests
arXiv:2607.09259v1 Announce Type: cross Abstract: Telecom fraud-control studies often stop at detector-level classification, but deployment use requires request-level policy resolution, lifecycle traceability, and auditability. This paper reframes fraud control as blockchain-linked auditable decision management for synthetic telecom/IoT fraud-control requests, and its main result is that the QLoRA-tuned LLM branch becomes much more usable than zero-shot prompting but mainly approaches, rather t
Geopolitical alignment: Endorsement effects in large language models
arXiv:2607.09262v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to summarize and evaluate policy-relevant information, but it remains unclear whether their judgments are implicitly shaped by geopolitical cues. I study this question with an endorsement experiment in which four LLMs evaluate the same international economic and security policies after each policy is randomly described as supported by the United States, the European Union, China, or Russia. In t
Risk-Aware General-Utility Markov Decision Processes
arXiv:2607.09298v1 Announce Type: cross Abstract: We study general-utility Markov decision processes (GUMDPs) with risk-aware objectives. In this framework, an agent aims to optimize a risk measure of the distribution of objective values, where the objective function depends on the frequency of visitation of states induced by the agent's policy. First, we motivate, propose, and formalize risk-aware GUMDPs, which enable agents and decision makers to trade off expected performance by risk aversio
Shortcut Trajectory Planning for Efficient Offline Reinforcement Learning
arXiv:2607.09336v1 Announce Type: cross Abstract: Diffusion-based trajectory planners have shown strong performance in offline reinforcement learning, but their iterative denoising process often incurs high inference cost. Consistency-based planners reduce the number of sampling steps, yet they typically rely on a two-stage teacher--student distillation pipeline that increases training cost and may introduce instability. We propose Shortcut Trajectory Planning (STP), an offline model-based rein
CtrlVTON: Controllable Virtual Try-On via Visual-Instance-Prompt Segmentation
arXiv:2607.09362v1 Announce Type: cross Abstract: Virtual try-on (VTO) has made significant progress in realistically transferring garments onto a target person. Yet most systems give the user little control over how a garment should be worn -- its size (loose or fitted), style (e.g., tucked in or untucked, open or closed), and spatial placement on the body. We address this gap with two complementary contributions. First, we define and solve Visual-Instance-Prompt Segmentation via VIP-SAM: give
Diversifying to Verify: When Task-Equivalent Programs Differ in Verifiability
arXiv:2607.09366v1 Announce Type: cross Abstract: Program verification is crucial for software correctness, but producing fully verified programs remains difficult in practice. This paper studies whether implementation structure affects automated verifiability when multiple generated programs are intended to satisfy the same task-level semantics. We present Diversify2Verify, a staged LLM-based pipeline for Why3 that infers representation-specific contracts, generates and tests diverse recursi
When Routes Run Out: Adversarial Co-Learning and Explainable Robustness in Quantum Repeater Networks
arXiv:2607.09378v1 Announce Type: cross Abstract: We study an adversarial bandit problem for entanglement-based quantum-network routing over a modest graph corpus. Alice selects an end-to-end repeater route for an Ekert-91 protocol (E91) representing her move, while Eve selects an attack surface, either edge intercept--resend or repeater memory degradation. Payoffs are drawn from cached SeQUeNCe-simulated E91 transcripts, and Alice accepts a turn when the finite-sample statistic violates the Cl
STEEL: Sparsity-Aware Fused Attention for Energy-Efficient Long-Sequence Inference on AMD's XDNA NPU
arXiv:2607.09385v1 Announce Type: cross Abstract: The growing adoption of large language model-based agents within operating system workflows has increased the importance of energy-efficient inference on laptop-class systems-on-chip (SoCs). While cloud offloading remains common, it introduces reliability and privacy concerns that are particularly problematic for agentic workloads. Recent laptop SoCs, therefore, incorporate neural processing engines (NPUs) optimized for energy efficiency; howeve
Fully Trainable Deep Differentiable Logic Gate Networks and Lookup Table Networks
arXiv:2607.09399v1 Announce Type: cross Abstract: We introduce a novel method for both partial and full optimization of the connections in deep differentiable logic gate networks (LGNs) and lookup table networks (LUTNs). Our training method utilizes a probability distribution over a set of connections per gate/lookup table (LUT) input pin, selecting the connection with highest merit, all whilst the optimal gate types or LUT-entries are learned in parallel. We show that the connection-optimized
On-Device Adaptive Battery Power Prediction for Electric Vehicles
arXiv:2607.09400v1 Announce Type: cross Abstract: Adaptive power management in Electric Vehicles (EVs) requires accurate power prediction. Although deep learning models have emerged as highly effective for time-series forecasting in this domain, their performance is prone to degradation when exposed to data with distributions different from the training data. We introduce a novel approach that enables on-device learning in resource-constrained EV systems to continuously adapt pretrained battery
SVF-CR: Synchronized Visual-Facial Cross-Refinement for Multimodal Ambivalence and Hesitancy Recognition
arXiv:2607.09417v1 Announce Type: cross Abstract: Ambivalence and hesitancy are subtle behavioral states that are expressed through a combination of verbal content, facial behavior, visual context, and acoustic cues. Effective recognition therefore requires not only extracting informative unimodal representations, but also modeling how temporally aligned behavioral evidence interacts across modalities. In this paper, we propose a synchronized visual-facial cross-refinement framework (SVF-CR) wi
Parameter-Efficient Vision-Language Adaptation with Continuous Metadata Conditioning for Animal Re-Identification
arXiv:2607.09443v1 Announce Type: cross Abstract: Long-term animal re-identification (ReID) must remain robust to gradual morphological evolution and seasonal appearance shifts. Although recent vision-language models provide strong pretrained visual representations, adapting them to longitudinal ecological settings remains challenging, particularly under identity and temporal distribution shifts. We present a parameter-efficient CLIP adaptation framework for animal ReID and introduce a continuo
Practical Source Code Recovery from Binary Functions Using Anchor-Based Retrieval and LLM Reasoning
arXiv:2607.09452v1 Announce Type: cross Abstract: We present a practical pipeline for recovering source code from stripped binary functions by combining reverse engineering, anchor-based source code retrieval, and large language model reasoning. Our binary-to-source-code retrieval method attempts to identify the source function from a source code database, rather than generating approximate decompiled pseudocode. It extracts anchors such as strings, constants, external calls, and available func
What VGGT Knows About Overlap: Probing Geometric Foundation Models for Co-Visibility
arXiv:2607.09503v1 Announce Type: cross Abstract: A fundamental challenge in 3D reconstruction and robotic localization is co-visibility: determining which image pairs share overlapping visible surfaces, particularly in scenarios with minimal overlap. We demonstrate that VGGT implicitly encodes co-visibility as an emergent behavior: without any supervision for this task, its internal representations exhibit a clear hierarchical structure mirroring that of large language models, i.e. early layer
Failure as a Process: An Anatomy of CLI Coding Agent Trajectories
arXiv:2607.09510v1 Announce Type: cross Abstract: Large language model (LLM) coding agents are increasingly deployed to autonomously perform software engineering tasks in terminal-based environments, making their reliability a growing concern. Existing empirical studies investigate why coding agents fail, yet they largely treat failure as a final outcome rather than a temporal process, providing limited insight into how failures emerge, evolve, and become unrecoverable. We present the first lar
Terminal Dimension Reduction for Time Series with Applications
arXiv:2607.09490v1 Announce Type: cross Abstract: Terminal embeddings have emerged as a powerful tool for dimension reduction. Given a set of points $P\subset \mathbb{R}^d$, a terminal embedding is a mapping $f:\mathbb{R}^d\rightarrow \mathbb{R}^t$ that preserves the pairwise distance between any pair of points $p\in P$ and $q\in \mathbb{R}^d$ up to small distortion under this mapping. Terminal embeddings have been particularly fruitful for constructing $k$-means and $k$-median coresets, where
Predicting fixed-sample test decisions enables anytime-valid inference
arXiv:2602.13872v2 Announce Type: replace-cross Abstract: Statistical hypothesis tests typically use prespecified sample sizes, yet data often arrive sequentially. Interim analyses invalidate classical error guarantees, while existing sequential methods require rigid testing preschedules or incur substantial losses in statistical power. We introduce a simple procedure that transforms any fixed-sample hypothesis test into an anytime-valid test while ensuring Type-I error control and near-optimal
Knowledge Graphs and Explainable AI as Complementary Resources for Urban Mining
arXiv:2607.09578v1 Announce Type: new Abstract: Pre-demolition assessment, the regulated audit process at the heart of urban mining, is an information process in which AI support must serve qualified auditors who remain accountable for the decisions taken. The relevant unit of value is not prediction accuracy alone, but the defensibility of the supported decisions: their legibility, plausibility, sourcing, and contestability. Explainable AI techniques and domain knowledge graphs each address pa
SCATE: Learning to Supervise Coding Agents for Cost-Effective Test Generation
arXiv:2607.08983v1 Announce Type: cross Abstract: While autonomous coding agents have significantly advanced automated test generation, they remain fundamentally limited by lazy generation, a phenomenon where agents prematurely terminate tasks and systematically avoid complex programmatic logic, resulting in inadequate code coverage. Currently, mitigating this premature termination requires continuous human-in-the-loop supervision. This heavy reliance on human intuition creates a bottleneck tha
Seeing is Free, Speaking is Not: Uncovering the True Energy Bottleneck in Edge VLM Inference
arXiv:2607.09520v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are the perceptual backbone of embodied AI, but their energy footprint on edge hardware remains poorly understood. Existing efficiency efforts focus predominantly on reducing visual tokens, implicitly treating visual processing as the dominant energy cost. We overturn this implicit assumption through the first systematic energy profiling of on-device VLM inference, spanning five models across three architecture fami
ALICE: Learning a General-Purpose Pathology Foundation Model from Vision, Vision-Language, and Slide-Level Experts
arXiv:2607.09526v1 Announce Type: cross Abstract: Foundation models are reshaping computational pathology, yet their capabilities remain shaped by pretraining objectives, data sources, and spatial scales, fragmenting complementary expertise across separate backbones. Here we present ALICE, a unified foundation model trained through multi-stage agglomerative distillation that sequentially distills eight vision-only, vision-language, and slide-level teacher models into dedicated modules of a sing
Large-Scale Portfolio Optimization Problem Under Cardinality Constraint With Enhanced Multi-Objective Evolutionary Algorithms
arXiv:2607.09566v1 Announce Type: cross Abstract: Decision-making is posing an increasingly formidable challenge to investors because of the growing number of alternatives available in financial markets. A hot area of research over the past few decades has been portfolio optimization that seeks to determine how much an investor should invest in which asset. Introducing real-world conditions to the optimization model turns the problem into an NP-hard one for whose solution exact methods become i
PAC-ACT: Post-training Actor-Critic for Action Chunking Transformers
arXiv:2607.09590v1 Announce Type: cross Abstract: Precision industrial contact manipulation requires reliable robot policies under pose perturbations and contact-force constraints. Vision-language-action models offer broad generalization but often introduce high inference latency and GPU-memory cost, while vision-action chunking policies are more suitable for real-time industrial control. However, these policies are usually trained by behavior cloning and suffer from distribution shift in conta
4DR360: State Reasoning for Joint 3D Detection and Occupancy Prediction in 4D Radar-Camera Full-Scene Perception
arXiv:2607.09629v1 Announce Type: cross Abstract: Reliable autonomous driving requires full-scene perception that couples foreground objects with dense semantic layout. Recently, 4D millimeter-wave radar has emerged as a robust and affordable sensor, yet its sparse returns make radar-camera fusion necessary for comprehensive scene understanding. Existing radar-camera methods mainly optimize detection, while dual-task systems usually decode boxes and occupancy with limited interaction. To addres
Lean-QIT: Towards a Formal Infrastructure for Quantum Information Theory
arXiv:2607.09632v1 Announce Type: cross Abstract: Quantum information theory (QIT) characterizes the capabilities and fundamental limits of quantum information processing, underpinning quantum communication, computation, and error correction. Formalizing its coding theorems requires connecting finite-block protocols, analytic inequalities, and asymptotic limits within a unified machine-checked framework. Existing developments, however, lack a reusable operational layer that defines codes, error
Semantic Pareto-DQN: A Multi-Objective Reinforcement Learning Framework for Financial Anomaly Detection
arXiv:2607.09641v1 Announce Type: cross Abstract: Financial anomaly detection suffers from extreme class imbalance, causing traditional single-objective algorithms to exhibit ``fraud collapse'', defaulting to the majority class and failing to balance anomaly interdiction with customer friction. To overcome this without distortive data resampling, we propose the Semantic Pareto-DQN, a multi-objective reinforcement learning framework. Our approach synthesizes heterogeneous transaction features in
VEXAIoT: Autonomous IoT Vulnerability EXploitation using AI Agents
arXiv:2607.09653v1 Announce Type: cross Abstract: Internet of Things (IoT) systems are inherently vulnerable due to constrained hardware, outdated firmware, and insecure default configurations, creating a need for scalable and adaptive security testing approaches. While recent adoptions of Large Language Model (LLM) agents have demonstrated promise in penetration testing and Capture-the-Flag (CTF) environments, their application to IoT specific vulnerabilities remains unexplored. This paper pre
Evolution of Accuracy and Visual-Cognitive Errors in a Decade of Vision-Language AI Models
arXiv:2607.09654v1 Announce Type: cross Abstract: Vision language models (VLMs) have made remarkable progress in visual reasoning during the last decade. Most evaluations have used simple scenes (MS-COCO) that do not showcase complex human interactions or behaviors, only a handful of non-curated human descriptions as a benchmark, and have not focused on understanding the model's error types. Here, we introduce the Complex Social Behavior (CSB) dataset, containing 100 images depicting complex so
Scalable Visual Pretraining for Language Intelligence
arXiv:2607.09657v1 Announce Type: cross Abstract: The rapid progress of large foundation models has been driven predominantly by pretraining on large-scale text corpora. However, many forms of knowledge are conveyed through visual representations, where figures, typeset equations, and page layouts carry rich information that cannot be faithfully or completely captured by text alone. Yet current pretraining approaches discard these visual cues by converting visually rich sources, such as documen
PHINN-EEG: Topological Time-Series Analysis of Dream-State EEG -- Dynamic Betti Curves for Dream Content Classification and Topology-Conditioned Neural Signal Synthesis
arXiv:2607.09662v1 Announce Type: cross Abstract: Current electroencephalography (EEG)-based dream detection relies on power spectral density (PSD) and statistical moment features, achieving a state-of-the-art area under the receiver operating characteristic curve (AUC) of approximately 0.70 on the DREAM database (Wong et al., 2025, Nature Communications). We introduce PHINN-EEG (Persistent Homology Inspired Neural Network for EEG), the first topological time-series framework for dream mentatio
A Descriptive and Normative Theory of Human Beliefs in RLHF
arXiv:2506.01692v2 Announce Type: replace Abstract: Human preferences in RLHF are typically modeled as a function of the human's reward function or corresponding optimal state-action values. In this work, we propose that human beliefs about the capabilities of the agent being trained also play a key role in preference generation. We examine two questions related to this hypothesis, one descriptive and one normative, respectively: Do human labelers' beliefs about agent capabilities affect the pr
QAgent: An LLM-based Multi-Agent System for Autonomous OpenQASM programming
arXiv:2508.20134v2 Announce Type: replace Abstract: Programming quantum circuits at the OpenQASM level is essential for achieving hardware-aware optimization and reliable execution on noisy intermediate-scale quantum (NISQ) devices, yet it remains challenging due to the need for domain-specific planning, iterative code synthesis, and low-level calibration. In this paper, we present QAgent, the first autonomous multi-agent framework for end-to-end OpenQASM code generation. QAgent integrates sche
Beyond Embeddings: Interpretable Feature Extraction for Binary Code Similarity
arXiv:2509.23449v2 Announce Type: replace Abstract: Binary code similarity detection is a core task in reverse engineering. It supports malware analysis and vulnerability discovery by identifying semantically similar code in different contexts. Modern methods have progressed from manually engineered features to vector representations. Hand-crafted statistics (e.g., operation ratios) are interpretable, but shallow and fail to generalize. Embedding-based methods overcome this by learning robust c
Improving Language Agents through BREW: Bootstrapping expeRientially-learned Environmental knoWledge
arXiv:2511.20297v2 Announce Type: replace Abstract: Large Language Model (LLM)-based agents are increasingly capable of complex, multi-step tasks such as GUI automation, tool use, and data manipulation, yet they cannot learn from experience: each new session rediscovers solutions from scratch. We introduce BREW (Bootstrapping expeRientially-learned Environmental knoWledge), a framework that distills an agent's past interaction trajectories into a structured, retrievable knowledge base (KB) of n
A Self-Evolving Agentic Framework for Metasurface Inverse Design
arXiv:2604.01480v2 Announce Type: replace Abstract: Metasurface inverse design can realize complex optical functionality, but turning a target optical response into executable optimization code still requires substantial expertise in computational electromagnetics and solver-specific software engineering. We present a self-evolving agentic framework that lowers this barrier by coupling a coding agent, explicit human-readable skill files, and a deterministic physics-based evaluator. Rather than
Rectification Difficulty and Optimal Sample Allocation in LLM-Augmented Surveys
arXiv:2604.17267v2 Announce Type: replace Abstract: Large Language Models can generate synthetic survey responses at low cost, but their accuracy varies unpredictably across questions. We study the design problem of allocating a fixed budget of human respondents across estimation tasks when cheap LLM predictions are available for every task. Our framework combines three components. First, building on Prediction-Powered Inference, we characterize a question-specific rectification difficulty that
HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs
arXiv:2604.20140v2 Announce Type: replace Abstract: Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks. DPO optimizes for the likelihood of generating preferred over dispreferred responses in their entirety and lacks the granularity to provide feedback on subsections of many-step solutions typical of reasoning tasks. Existing methods excel at either stable preference learning (e.
Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement Learning
arXiv:2605.17393v2 Announce Type: replace Abstract: Coordination graphs are a central abstraction in cooperative multi-agent reinforcement learning (MARL), yet existing sparse-graph learners lack a theoretically grounded mechanism to decide which edges should exist and how much information each edge should carry. Current methods rely on heuristic criteria that offer no formal guarantee on the learned topology, and no principled way to allocate different communication capacities to structurally
Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
arXiv:2606.00726v2 Announce Type: replace Abstract: Strong reasoning depends not only on model knowledge but also on how effectively cognitive behaviors are deployed during generation. Existing methods often rely on explicit behavior-level control, making them insufficiently adaptive when failures and required corrections vary across reasoning states, tasks, and models. To this end, we propose Latent Reward Steering (LRS), an adaptive inference-time framework that promotes cognitive behaviors b
Coding-agents can replicate scientific machine learning papers
arXiv:2607.02134v2 Announce Type: replace Abstract: Scientific machine learning papers typically make computational claims, e.g., that the relative mean square error is less than 5% or that the 95% predictive credible interval covers the test data. A coding agent can be prompted to replicate those claims from paper materials alone, but the prompt does not by itself reliably preserve progress or check whether generated evidence supports the paper's claims. We introduce Paper-replication, a workf
Projection Methods for Operator Learning and Universal Approximation
arXiv:2406.12264v5 Announce Type: replace-cross Abstract: We obtain a new universal approximation theorem for continuous (possibly nonlinear) operators on arbitrary Banach spaces using the Leray-Schauder mapping. Moreover, we introduce and study a method for operator learning in Banach spaces $L^p$ of functions with multiple variables, based on orthogonal projections on polynomial bases. We derive a universal approximation result for operators where we learn a linear projection and a finite dim
Transformer-Empowered Actor-Critic Reinforcement Learning for Sequence-Aware Service Function Chain Partitioning
arXiv:2504.18902v3 Announce Type: replace-cross Abstract: In the forthcoming era of 6G networks, characterized by unprecedented data rates, ultra-low latency, and ubiquitous connectivity, effective management of Virtualized Network Functions (VNFs) is essential. VNFs are software-based counterparts of traditional hardware devices that facilitate flexible and scalable service provisioning. Service Function Chains (SFCs), structured as ordered sequences of VNFs, are pivotal in delivering complex
M4V: Multimodal Mamba for Efficient Text-to-Video Generation
arXiv:2506.10915v2 Announce Type: replace-cross Abstract: Text-to-video generation has significantly enriched content creation and holds the potential to evolve into powerful world simulators. However, modeling the vast spatiotemporal space remains computationally demanding, particularly when employing Transformers, which incur quadratic complexity in sequence processing and thus limit practical applications. Recent advancements in linear-time sequence modeling, particularly the Mamba architect
Single-Frame Point-Pixel Registration via Supervised Cross-Modal Feature Matching
arXiv:2506.22784v2 Announce Type: replace-cross Abstract: Point-pixel registration between LiDAR point clouds and camera images is a fundamental yet challenging task in autonomous driving and robotic perception. A key difficulty lies in the modality gap between unstructured point clouds and structured images, especially under sparse single-frame LiDAR settings. Existing methods typically extract features separately from point clouds and images, then rely on hand-crafted or learned matching stra
Explaining Human Choice Probabilities with Simple Vector Representations
arXiv:2511.03643v3 Announce Type: replace-cross Abstract: We formalize human choice behavior in a probabilistic hide-and-seek task. In our geometric construction, vectors represent participant choice frequencies as well as probability matching and maximizing strategies. We measured choice behavior not just in the well-studied scenario of pursuing an objective (seeking), but also the rarely studied scenario of avoiding consequences (hiding). We used our geometric construction to define the avoid
H3Former: Hypergraph-based Semantic-Aware Aggregation via Hyperbolic Hierarchical Contrastive Loss for Fine-Grained Visual Classification
arXiv:2511.10260v2 Announce Type: replace-cross Abstract: Fine-Grained Visual Classification (FGVC) remains a challenging task due to subtle inter-class differences and large intra-class variations. Existing approaches typically rely on feature-selection mechanisms or region-proposal strategies to localize discriminative regions for semantic analysis. However, these methods often fail to capture discriminative cues comprehensively while introducing substantial category-agnostic redundancy. To a
AutoGraphAD: Unsupervised network anomaly detection using Variational Graph Autoencoders
arXiv:2511.17113v3 Announce Type: replace-cross Abstract: Network Intrusion Detection Systems (NIDS) are essential tools for detecting network attacks and intrusions. While extensive research has explored the use of supervised Machine Learning for attack detection and characterisation, these methods require accurately labelled datasets, which are very costly to obtain. Moreover, existing public datasets have limited and/or outdated attacks, and many of them suffer from mislabelled data. To redu
RIS-Assisted Downlink Pinching-Antenna Systems: GNN-Enabled Optimization Approaches
arXiv:2511.20305v2 Announce Type: replace-cross Abstract: This paper investigates a reconfigurable intelligent surface (RIS)-assisted multi-waveguide pinching-antenna (PA) system (PASS) for multi-user downlink information transmission, motivated by the unknown impact of the integration of emerging PASS and RIS on wireless communications. First, we formulate sum rate (SR) and energy efficiency (EE) maximization problems in a unified framework, subject to constraints on the movable region of PAs,
Data-Driven Learnability Transition of Measurement-Induced Entanglement
arXiv:2512.01317v3 Announce Type: replace-cross Abstract: Measurement-induced entanglement (MIE) captures how local measurements generate long-range quantum correlations and drive dynamical phase transitions in many-body systems. Yet estimating MIE experimentally remains challenging: direct evaluation requires extensive post-selection over measurement outcomes, raising the question of whether MIE is accessible with only polynomial resources. We address this challenge by reframing MIE detection
ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learning
arXiv:2512.16861v2 Announce Type: replace-cross Abstract: Long-horizon manipulation has been a long-standing challenge in the robotics community. We propose ReinforceGen, a system that combines task decomposition, data generation, imitation learning, and motion planning to form an initial solution, and improves each component through reinforcement-learning-based fine-tuning. ReinforceGen first segments the task into multiple localized skills, which are connected through motion planning. The ski
Transition Matching Distillation for Fast Video Generation
arXiv:2601.09881v2 Announce Type: replace-cross Abstract: Large video diffusion and flow models have achieved remarkable success in high-quality video generation, but their use in real-time interactive applications remains limited due to their inefficient multi-step sampling process. In this work, we present Transition Matching Distillation (TMD), a novel framework for distilling video diffusion models into efficient few-step generators. The central idea of TMD is to match the multi-step denois
Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization
arXiv:2602.07764v2 Announce Type: replace-cross Abstract: Multi-objective reinforcement learning (MORL) seeks to train agents capable of balancing conflicting objectives. While single preference-conditioned policies offer a highly scalable solution, existing approaches remain brittle in practice, frequently failing to recover dense Pareto fronts. We demonstrate that this failure stems from two structural pathologies: destructive advantage cancellation caused by premature Early Scalarization (ES
Knowledge-Based Design Requirements for Generative Social Robots in Higher Education
arXiv:2602.12873v5 Announce Type: replace-cross Abstract: Generative social robots (GSRs) powered by large language models enable adaptive, conversational tutoring but also introduce risks such as misinformation, overreliance, and privacy violations. Existing frameworks for educational technologies and responsible AI primarily define desired behaviors, yet they rarely specify the knowledge prerequisites that enable generative agents to express these behaviors reliably. To address this gap, we a
Empowering 9-1-1 Calltaking Training with Generative AI: Experiences and Lessons Learned
arXiv:2602.13241v3 Announce Type: replace-cross Abstract: Emergency call-takers form the first operational link in public safety response, handling over 240 million calls annually while facing a sustained training crisis: staffing shortages exceed 25\% in many centers, and preparing a single new hire can require up to 720 hours of one-on-one instruction that removes experienced personnel from active duty. Traditional training approaches struggle to scale under these constraints, limiting both c
The LLMbda Calculus: AI Agents, Conversations, and Information Flow
arXiv:2602.20064v2 Announce Type: replace-cross Abstract: Large language models are increasingly deployed as agents: they plan, call tools, read untrusted data, and act on the results. This exposes them to prompt injection: data meant only to be read is obeyed as an instruction. The most principled defences replace content inspection with provenance: classifying data by source and keeping trusted and untrusted apart through a separation of duty (the dual-LLM pattern) and information-flow contro
SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution
arXiv:2603.13428v3 Announce Type: replace-cross Abstract: Real-world software must continuously evolve to meet ever-changing and open-ended requirements. AI agents, increasingly deployed as long-running systems, are now entrusted to drive this evolution. Yet, existing benchmarks evaluate agents on isolated, one-off coding tasks, neglecting the temporal dependencies and technical debt inherent in real-world software evolution. To bridge this gap, we introduce DeepCommit, an agentic pipeline that
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
arXiv:2606.03979v2 Announce Type: replace-cross Abstract: The past few decades have witnessed significant advances in the design of machine learning algorithms, from early studies on task-specific shallow models to more general deep Large Language Models (LLMs). Despite showing promising results in tasks that require instant prediction or in-context learning, existing models lack the ability to continually learn and effectively transfer their temporal in-context knowledge to their long-term par
TCLA: Training-Free Class-wise Logit Adaptation for Medical Vision-Language Models
arXiv:2607.09562v1 Announce Type: cross Abstract: Medical Vision-Language Models (VLMs) exhibit strong zero-shot performance, yet their effectiveness still declines on out-of-distribution (OOD) data due to domain shifts and class bias inherited from large-scale pretraining. Existing few-shot adaptation methods typically introduce additional trainable components, which can be unstable in extremely low-data regimes (e.g., 1-shot), and lack robustness on different medical data. We present TCLA, a
ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL
arXiv:2606.31650v2 Announce Type: replace-cross Abstract: Long-horizon language agents must repeatedly interact with tools, accumulate evidence, and make decisions under bounded context windows. Context-management methods make such rollouts feasible by simplifying past interactions through deletion, folding, or memory editing. However, when useful history is collapsed into compressed states, the reconstructed context may no longer reveal which earlier observations support a successful final ans
Training, Reading, and Editing Legible Transformers
arXiv:2607.08946v1 Announce Type: cross Abstract: A transformer can be built from operators that are legible by construction -- bounded, named units that read as fuzzy set operations rather than dense activations -- but legibility must be pressed for during training, and the pressure has a failure mode. A crispness penalty meant to sharpen a bounded operator into a decisive detector instead collapses it into a dead constant. An identity, E[v(1-v)] = mu(1-mu) - var, shows why -- the penalty is a
ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models
arXiv:2607.09134v1 Announce Type: cross Abstract: Representation alignment (REPA) has been investigated to accelerate diffusion training, but we observe that regularizing intermediate representations in diffusion Transformers (DiT) may implicitly entangle latents and limit generative capacity. To address this issue, we propose ReGen, a hierarchical multi-prompt representation generation framework that jointly estimates multiple vector fields for both representations and data within a single dif
SmartCall v1.0.1 发布 新增通义千问语音模型
:book: 项目简介 SmartCall 是一套基于 AI 大模型 + Asterisk 通信引擎构建的新一代智能客服呼叫中心系统。系统深度融合了 AI 语音机器人、智能 IVR 流程编排、实时语音识别（ASR）、语音合成（TTS）、大模型意图识别 等核心能力，为企业提供从呼入智能应答到智能外呼的全链路 AI 客服解决方案。 无论是电商售后、金融催...
你这图「保真」吗？AI 生图时代的信息防伪
人类记录信息的方式一直在变化，但我们对「真实性」的需求从未改变。查看全文
零代码接口测试 APIAuto 6，AI Agent 自动操作&读写 DB :fire: Star 2K+
APIAuto-机器学习 HTTP 接口工具 敏捷开发最强大易用的 HTTP 接口工具，机器学习零代码测试、生成代码与静态检查、生成文档与光标悬浮注释。 提供集 文档、测试、Mock、调试、管理 于一体的一站式体验，还有一键 格式化、注释/取消注释 等高效快捷键。 在常用功能上远超 Postman, Swagger, YApi, Rap 等其它各种 开源、商...
用 Solon AI ReActAgent 落地智能客服工单处理
某电商平台售后工单日均 5,000+，人工处理有三个老大难： 痛点 表现 后果 响应慢 首响经常要等很久 客户满意度下降 处理不一致 同样“丢件”，不同客服结果不同 投诉升级 重复劳动 大量工单是同一类问题 人力被低价值查询占满 核心矛盾：工单量增速明显快于客服团队扩编速度。 一、业务方案 1.1 目标 常见问题由 Agent ...
ShowDoc AI 智能体上线
ShowDoc 是一个在线文档管理系统，用于管理和分享项目文档，支持 API 文档、技术规范、产品说明、团队知识库等场景。 本次更新主要上线了 AI 智能体，项目成员可以直接用对话找文档、问内容、一句话批量建页面，还能全项目批量改一个点（比如统一换域名、补说明、归类），让 AI 在编辑器里帮你改稿、用对话管项目和看板任...
派早报：苹果起诉 OpenAI 窃取商业机密
苹果起诉 OpenAI 窃取商业机密变压器短缺掣肘数据中心扩张世界杯带动小红书使用时长大幅提升废弃 IBM 园区成网红景点SpaceX 申请发射十万颗卫星高技能人士正大规模「打零工」参与模型训练看看就行的简讯少数派的近期动态你可能错过的好文章查看全文
面向 Qwen 系列模型线性注意力的高性能优化实践｜AICon深圳
点击查看原文>
98年哈工大教授创业，要做人形灵巧操作世界模型
从采集触觉，到对齐触觉，再到使用触觉
An Agent in 100 Lines of Lisp
Comments
老黄RTX Spark真机现身Bilibili World！CPU和GPU直接焊在一起，笔记本跑120B大模型
老黄在ComputeX发布的“超级芯片”，已经在真机中落地了
近百名玩家涌入具身数据：一年融资44.7亿，谁能真靠“卖数据”赚钱？
为了帮你看清具身数据行业，我们总结了以下十个行业现状