TILens Daily Edition 2026-10-26 Filters: topic=ai, github=hidden Stats: 500 articles, 26 sources, 442 research papers Top topics: AI, AI Research, Information Retrieval ## News - Greptile takes bug detection beyond code review with GPT-6 Astra Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/greptile-code-review-codex-astra - OpenAI GPT-6.1 Terra is now generally available on Amazon Bedrock Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/10/openai-gpt-6-1-terra-on-amazon-bedrock/ - Introducing GPT-6.1 Terra Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/introducing-gpt-6-1-terra - Making Failure Diagnosis Reliable with Pensive AI Source: netflix-techblog Topic: Architecture (+AI) URL: https://netflixtechblog.com/making-failure-diagnosis-reliable-with-pensive-ai-6b0811a1c015?source=rss----2615bd06b42e---4 - Working with academic communities to build scientific understanding Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/building-scientific-understanding-with-academic-communities - GPT-6.1 Sol helps CodeRabbit strengthen security across complex codebases Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/gpt-6-1-sol-coderabbit-code-security - ChatGPT’s expanding world of work Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/chatgpt-expanding-world-of-work - How Ultrafast cut incident investigation from hours to minutes at OpenAI Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/openai-cut-incident-investigation - How Fanatics and OpenAI streamline the fan experience Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/fanatics-streamline-fan-experience - Spring Office Hours Podcast: S5E27 - Hugging Face for Java Developers with Pratik Patel Source: spring-blog Topic: Java (+AI) URL: https://spring.io/blog/2026/10/26/spring-office-hours-podcast-S5E27 - Humanity can't afford not to spend $800B on AI, Anthropic insists Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/10/26/humanity-cant-afford-not-to-spend-800b-on-ai-anthropic-insists/5305580 - OpenAI rolls out budget-priced mid-tier GPT-6.1 Terra Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/10/26/openai-rolls-out-budget-priced-mid-tier-gpt-61-terra/5305574 - OpenAI halved its agent’s price. Its own safety report flagged a catch. Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-terra-bypassed-restrictions/ - How to Build a Simple Data Analyzer in Python with Pandas Source: freecodecamp Topic: General (+AI) URL: https://www.freecodecamp.org/news/how-to-build-a-simple-data-analyzer-in-python-with-pandas/ - Track New Jobs at Your Target Companies Straight From Their ATS (Greenhouse, Lever, Ashby, Workday) Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/dedicated_crest/track-new-jobs-at-your-target-companies-straight-from-their-ats-greenhouse-lever-ashby-workday-5dk3 - How to make a product launch video with Claude Code and HyperFrames (HTML to MP4) Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/dedupedai/how-to-make-a-product-launch-video-with-claude-code-and-hyperframes-html-to-mp4-1ab5 - Amateur astronomer harnesses AI to find a possible hidden exoplanet Source: adafruit-blog Topic: Hardware (+AI) URL: https://blog.adafruit.com/2026/10/26/amateur-astronomer-harnesses-ai-to-find-a-possible-hidden-exoplanet/ - Most of Anthropic’s Q3 revenue came from models that barely existed six months ago Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/anthropic-s1-models-revenue/ - Will the real Anthropic please stand up Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/10/26/1147672/will-the-real-anthropic-please-stand-up/ - Anthropic’s IPO filing reveals its strategy for keeping enterprise customers hooked Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/26/anthropics-ipo-filing-reveals-its-strategy-for-keeping-enterprise-customers-hooked/ - Vector Search for Java Developers: HNSW Intuition and pgvector in Practice Source: java-code-geeks Topic: Java (+AI, PostgreSQL) URL: https://www.javacodegeeks.com/2026/10/vector-search-for-java-developers-hnsw-intuition-and-pgvector-in-practice.html - Everything That Happened in AI Today (Tuesday, October 27, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-tuesday-october-27-2026/ - Trumpets blare and skies part as AI hypefest culminates in Anthropic IPO filing Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/10/26/trumpets-blare-and-skies-part-as-ai-hypefest-culminates-in-anthropic-ipo-filing/5305456 - AI-assisted PCB design for KiCAD 10 using MCP Source: adafruit-blog Topic: Hardware (+AI) URL: https://blog.adafruit.com/2026/10/26/ai-assisted-pcb-design-for-kicad-10-using-mcp/ - Anthropic officially files for its public debut Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/26/anthropic-officially-files-for-its-public-debut/ - Claude Code’s top enterprise users outspend other Claude users 20 to 1, Anthropic’s IPO filing says Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/claude-codes-enterprise-20-to-1/ - When 110 humanoids hit the dance floor Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/when-110-humanoids-hit-the-dance-floor - JSON Schema Structured Summarization in Node.js: OpenAI GPT Endpoint Retry Design 2026 Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/elibennett128/json-schema-structured-summarization-in-nodejs-openai-gpt-endpoint-retry-design-2026-5epe - ChromaDB: Embeddings and Vector Databases in Python Source: real-python Topic: Python (+AI) URL: https://realpython.com/chromadb-vector-database/ - The sandbox wasn’t enough: Why AI agent governance requires runtime observability Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/ai-agent-runtime-observability/ - Import AI 478: Math for alignment; ProgramBench; and Mirendil shows what RSI means Source: importai Topic: AI URL: https://importai.substack.com/p/import-ai-478-math-for-alignment - Article: The Evolution of Agentic Harnesses: From Chains to Graph to Code Source: infoq-architecture Topic: Architecture (+AI) URL: https://www.infoq.com/articles/agentic-ai-architecture-harness-evolution/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design - 😺 Claude crossed a paywall on its own Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/claude-crossed-a-paywall-on-its-own/ - Euro open source specialist proposes LLM gateway to ease token bills Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/10/26/euro-open-source-specialist-proposes-llm-gateway-to-ease-token-bills/5305170 - Kimi continues to challenge the frontier with K3.1 Pro Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/kimi-continues-to-challenge-the-frontier-with-k3-1-pro - The focus on AI safety disasters ignores everyday harms Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/10/26/1147645/the-focus-on-ai-safety-disasters-ignores-everyday-harms/ - Introduction to the NVIDIA Triton Java API Source: java-code-geeks Topic: Java (+AI) URL: https://www.javacodegeeks.com/introduction-to-the-nvidia-triton-java-api.html - From Bug Hunting to Verification: Anthropic’s Next Software Security Experiment Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/anthropic-claude-software-security-verification/ - OpenAI Takes Frontier Training Offline. Can Simulations Prepare Agents for the Real Web? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/openai-frontier-training-offline-simulations/ - Everything That Happened in AI Today (Monday, October 26, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-monday-october-26-2026/ ## Research - What Makes AI-Written Stories Feel Off? Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/what-makes-ai-written-stories-feel-off/ - Opening the Box: Can Machine Learning Resolve Schrödinger’s Cat? Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/opening-the-box-can-machine-learning-resolve-schrdingers-cat/ - My Machine Learning Pipeline Cheated, and Cross-Validation Never Noticed Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/my-machine-learning-pipeline-cheated-and-cross-validation-never-noticed/ - Claude Code vs. Cursor: What a Field Test Shows That the Feature Comparisons Miss Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/claude-code-vs-cursor-what-a-field-test-shows-that-the-feature-comparisons-miss/ - SkillRep: Characterizing and Understanding the Representation Design Space of Agent Skill Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.32336 - Machine-Readable Operator Manuals over the ISO 11783 Network for Offline, Multilingual LLM Assistance Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.31863 - MICE to Meet You: From Re-ranking Only to End-to-End Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.31932 - A Model-Agnostic Correction Framework for Short-Term Building Load Forecasting Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.31959 - UAE GovTrust Scope Filtering Gains and Routing Failures in Bilingual Public Service Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.32608 - Hierarchical GTV Estimation: Bridging the Gap between Container-Level Ranking and Item-Level Conversion Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.32420 - PersonalQuery-Benchmark:Evaluating Retrieval Robustness to Personalized User Expression Differences Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.32164 - Separating Thinking from Spelling for Efficient Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.32980 - Deep learning enables urban change profiling through alignment of historical maps Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2602.02154 - From archive to resource: bringing legacy data back to life at scale with large language models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.32616 - Driving Video Retrieval for Complex Queries with Structured Grounding Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.09109 - Knowledge Distillation across Item and Code Spaces for Parallel Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.32943 - Scaling Graph Query Processing: Focused Exploration on Partitions Using Load Balancing Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.32015 - Agentic Memory Management Is the Next Frontier of Information Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.32464 - System One models Are Not Better Rerankers Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.32318 - Every Edge Needs a Quote: Building a Quote-Grounded Knowledge Graph of Healthcare Software Adoption with Language-Model Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research, JavaScript, React) URL: https://arxiv.org/abs/2610.32781 - Lean Finder V2: Semantic Search for Mathlib That Disambiguates User Queries Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.30843 - What the Query Remembers: Query Abstraction Governs Lexical and Dense Retrieval of Classical Arabic Poetry Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.31821 - Mining Frames: Association Rule Mining as an Unsupervised Framework for News Framing Detection Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.31874 - From Item Scores to Semantic Tokens: Test-Time Collaborative Adaptation for Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.32098 - Data Quality in RVL-CDIP: A Systematic Audit Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32126 - Constitution-Guided Watermarking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09552 - EvoSkill v2: Fully Agentic Skill Evolution from Benchmark Adaptation to a Stateful Evolver Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25931 - From Promises to Accountability: Comparative AI Modeling and Visualization of Electoral Commitments in Nepali Political Texts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32150 - A survey of diversity quantification in natural language processing: The why, what, where and how Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.20858 - Acoustic and Lexical Signals for Native Language Identification of Language Learners Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32382 - AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20625 - J-Comm: Jacobian-Guided Latent Communication between LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32871 - Reading Between the Layers: Cross-Modal Alignment and Representational Hierarchy in Vision Transformers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32463 - Many Perturbations, Shared Failure Dynamics: Tracing Direction-Sensitive Perturbation Influence in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32309 - Knowledge Graphs Quality Assessment in the Era of LLMs: A Conceptual Framework Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31684 - SCI-AGENT-EXAM: Benchmarking Agents on Scientific Research Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32441 - LeakScale: Estimating the Causal Effect of Benchmark Exposure Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27176 - Putting Transformer Theories to the Test Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32104 - A Guideline-Augmented Multi-Agent Framework for Schema-as-Code Biomedical Named Entity Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02970 - Why Full-Duplex Speech Models Collapse in Long Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32349 - Communicating with the Entire Population: Machine Translation of Emergency Alerts and Warnings Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32842 - Translators as Invisible Teachers of AI: Copyright, Translation Memory, and the Political Economy of Linguistic Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24842 - Which Answer Did the Seventeen-Year-Old Write? A Behavioral Case Study of Author-Age Misattribution, Miscalibrated Confidence, and Non-Corrective Self-Explanation in Six Frontier Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31946 - Multiplicative vs. Additive State Coupling in Learned Optimizer Schedules Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32801 - From Target Selection to Condition Reuse: Auditing Residual Interventions in Tool-Use Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31686 - Natural Language Autoencoders Identify Without Explaining Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32691 - OACap: Caption-Guided Active Observation for Detailed Video Captioning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29327 - Rethinking Structured Generation: Can Graph-Based Reasoning Resolve Ambiguity? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31681 - Profile-Driven User Simulation via Reinforcement Learning with Hierarchical Rewards for Task-Oriented Dialogues Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32435 - SWE-Clar: Can Coding Agents Clarify Incomplete Client Requirements and Deliver Greenfield Software? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31854 - Multi modal perceived conversation success prediction for spontaneous autistic and non-autistic dyadic interactions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31682 - AgentGUI: An Interface for Observing and Steering Long-Running AI Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.26300 - Accordion: Elastic-Depth Inference via Fixed-Prefix Layer Looping Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32492 - Interpretable sparse fine-tuning with TopKLoRA enables faithful circuit discovery Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32866 - MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.09983 - RCEM: Robust Conversational Search EMbedder in Distributional Shift Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01697 - Scaling Laws for Safety Probes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30678 - Knowing Whom to Trust is not Enough: The Trust--Agreement Gap in Repeated Multi-Party LLM Negotiation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31971 - The Butterfly Defects: Tracing Cooperation in LLM Agent Networks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32726 - SWE-Shift: Evaluating Coding Agents in Evolving Workspaces Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32196 - Romanized Arabic Across Dialects: Views, Usage Patterns, and Linguistic Variation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02555 - Ontology-Guided Knowledge Graph Construction from Structured Metadata and Climate Science Publications Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32725 - From Noisy Retrieval to Decision Evidence: Silver Evidence Demonstrations for In-Context Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32128 - Do Halting Heads Really Save Compute in Looped Language Models? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32246 - Aligning Large Language Models with Human Feedback: Mathematical Foundations and Algorithm Design Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31862 - Behaviour analysis for large language model-driven agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32087 - EvalCards: A Framework for Standardized Evaluation Reporting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.21695 - Same Context, Different Agents: A Behavioral Study of Semantic Layers, Multi-Agent Orchestration and Memory Compaction in Data Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20959 - TaxoSAE: Rethinking Sparse Autoencoders through Taxonomic Logic Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31894 - Disentangling Question, Response, and Verifier Languages in Multilingual P(True) Self-Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32144 - AfriGuard: Safety and Robust Refusal For African Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26474 - Validating the Comparison, Not Just the Scorer: Why Overall Accuracy Can Mislead in Interactive LLM Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31678 - Under the Influence: Evaluating and Improving LLM Vigilance in Agentic Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.21262 - DraMaze: A Multi-Agent Pipeline with Future-Aware Memory for Diverse Microdrama Script Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32002 - Beyond Static and Linear: What Attention Constraints Best Fit Human Reading Times? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23818 - Continuous Audio Thinking for Large Audio Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18273 - Depth-Dependent Safety Geometry in Vision-Language Models: Layer-Wise Localization and Bidirectional Refusal Control Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32182 - NodeSyn: Socially Aligned Synthetic Data for AI Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14381 - How Much Do You Trust A Dog? Quantifying Hint-Following in Reasoning Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32055 - The Schema Coherence Inventory: Measuring Whether an Assigned Belief Organizes a Language Model's Cognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31683 - The Punjabi Geet Toxicity Dataset (PGT-FG): Fine-Grained Multimodal Annotations for Toxic Content in Punjabi Songs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32513 - Knowing When to Stop: The Evidence-Action Gap in Coding Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31895 - When Humans Leave Context Unsaid: Implicit Context as a Risk for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09551 - REACT: Representational Early Analysis and Control of Chain-of-Thought Trajectories Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.32113 - KrishokTech: A Bengali Agricultural Advisory System with Explicit Authorization Controls Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32817 - Probing Collision Grounding in Vision-Language Models for Safe Human-Robot Collaboration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.31196 - Pseudo-Labels as Rewards, Not Targets: Group-Relative Policy Optimization for Semi-Supervised ASR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32572 - "Not" is Not Lost in Translation: A Causal Analysis of Negation Representations in Multilingual LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32281 - Efficient Benchmarking Is Just Feature Selection and Multiple Regression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25773 - DIAL-S2ST: Learning Latency Control for Simultaneous Speech-to-Speech Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32214 - Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10623 - The LLENS Platform for On-Premises Large Language Model Agents in a Japanese University Hospital: Development and Evaluation Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32151 - Deep Reasoning in General Purpose Agents via Structured Meta-Cognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11388 - How Ground Truth Shapes Retrieval Scores: Evidence-Aware Evaluation of a Retrieval-Augmented Generation System for Breast Lesions Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.31606 - ActionRAG: Evidence-Refining Graph Diffusion for Long-Term Memory in LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32752 - MedAction: Towards Active Multi-turn Clinical Diagnostic LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07305 - Scaling cross-situational word learning on children's naturalistic experiences Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31842 - Latent Coherence: Do Frontier Language Models' Probability Judgments Obey the Law of Total Probability? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31833 - Adaptive Frequency Threshold Byte Pair Encoding for Mixed Natural Language and Structured Symbolic Corpora Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32921 - PHYRD: A Living Benchmark for Reproducing and Extending Theoretical Physics Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32575 - Mostly Reading: What Open-Book Scores Measure in Document-Level LoRA Adapters Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31017 - GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.31105 - Beyond Post-Hoc Rewards: Privileged Reasoning Exploration for Multimodal Embeddings Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32474 - Frontier-OPD: Discovering the Edge of Agent Capability and Teaching Agents to Go Beyond Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32802 - PAIR-SAFE: A Paired-Agent Approach for Runtime Auditing and Refining AI-Mediated Mental Health Support Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.12754 - Collection-Date Assignment Redirects Answers in Temporal QA Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32191 - Token-Set Choice Confounds POPE: A Systematic Audit of Yes/No Extraction in VLM Hallucination Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25964 - Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06840 - Distributional Alignment of LLMs and Its Generalization Properties Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31687 - How Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07891 - Muse Glimmer 30B: An On-Device Agentic Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24628 - Decoupling Patient Personas and Clinical Workflows: A Dual-Agent Approach to Realistic Medical Dialogue Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32443 - ToolRACER: A Robust Agentic Conversation Emulation Resource for Agent Training and Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09163 - Towards robust long-context understanding of large language model via active recap learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13734 - CrimeNER: Curated Dataset and Methods for Research and Investigation in Language Intelligence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02150 - Semantically Rich, Metrically Affect-Blind: A Geometric Blind Spot in Modern Text Embedders Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32122 - Tampered ML: Evaluating LLM Judgment of Machine Learning Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32114 - POS-Signature Demonstration Retrieval for In-Context Dependency Parsing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31966 - LazyFlash: Forward-Dense, Backward-Sparse Attention for Accelerated Long-Context Fine-Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31911 - Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.27457 - MisconceptDialogue: Evaluation Criteria Shape Measured Success in LLM Math Tutoring Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31679 - Not All Information Is Worth Asking For: Decision-Informed Information Seeking with LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32181 - A Diversity Diet for a Healthier Model: A Case Study of French ModernBERT Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22014 - CRM-Agent-Bench: Benchmarking Tool-Using Agents in Stateful Enterprise Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32004 - Better Reward Models Are Not Always Less Biased: Social Alignment Beyond Standard Reward Benchmarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05003 - BabelArena: A Large-Scale Multilingual Benchmark for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23490 - Concentrated Causal Influence, Distributed Diagnostic Information: Cognitive Impairment Decisions in Large Audio-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32061 - SPOOK: Sparse Pixel Optimization for Off-Manifold Knowledge in Vision Encoders Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32835 - When Agents Fail: Model or Harness--Who's to Blame? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32483 - On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32770 - LAMB: A Modern Contextual Language Model for Latin Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31723 - SyncPro: Synchronous Reasoning and Responding for Proactive Streaming Video Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32132 - A-MapReduce: Executing Wide Search via Agentic MapReduce Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01331 - SAGE: Sense-Aligned Multimodal Grounding Evaluation with Gloss-Augmented Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31838 - SOPO: Socratic Guided Policy Optimization for Span-Level Hallucination Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32212 - Context or Knowledge: How LLMs Attribute Their Own Answers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32109 - DMAIC-Bench: From Self-Reflection to Self-Restraint for Agents in Multi-Stage Analytical Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32305 - Omni-UBench: Benchmarking Omni-Modal LLM-based Guardrails Across Safety, Utility, and Reliability Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31713 - The Language of Instruction: Genre and Generative AI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32982 - Shorter Is Not Cheaper: A Controlled Comparison of Declarative Animation Specifications and Free-Form Code for LLM-Generated Explanations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32129 - The Helpful Agent Problem: When Emergent Cooperation Among LLM Agents Bypasses Intended Workflows Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31985 - GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05369 - ASTOR: Benchmarking and Improving Autoformulation for Soft-Constraint Optimization with a Formal Grammar Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26819 - Residual Expert Routing for Text-Only Domain Adaptation of Factorized Transducer ASR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32637 - Yalda-Embedding: Open Development of a Competitive Persian Retrieval Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32933 - CounselPlex: A Stressor-Aware Full-Duplex Counseling Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32702 - Chinese Decision: A Family of Language Models for Single-Pass Probabilistic Decision-Making Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23170 - What MLLMs Learn about When they Learn about Multimodal Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.01719 - Persona-Guided LLM Agents for Task-Oriented Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18085 - Analysing Austrian Parliamentary Speeches by Predicting Party Affiliations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32515 - Free Lunch for LLMs Confidence: The RL Critic Already Knows Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31820 - JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19913 - Dementia-R1: Reinforced Pretraining and Reasoning from Unstructured Clinical Notes for Real-World Dementia Prognosis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.03018 - 4DMemory: Benchmarking Long-Horizon Spatiotemporal Memory with Harness-Augmented Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32332 - Principled Nonlinear Concept Erasure and Steering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32516 - Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20179 - A Broader Look into MLLM's Retrieval Heads Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32411 - SteerEval: Inference-time Interventions Strengthen Multilingual Generalization in Neural Summarization Metrics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15809 - Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16647 - TreeWY: Speculative Verification for Gated DeltaNet Hybrids Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20961 - Agreement rather than normalisation keeps depth reusable in looped language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31943 - Beyond What to Say: Proactive Utterance Timing with Inner Thoughts for Werewolf Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32107 - AusClinBench: a deterministically scored benchmark of large language models against current Australian clinical policy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31993 - Rethinking SAE Evaluation: An Atomic Interpretable Unit Framework Reveals Hidden Polysemanticity and Redundancy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30474 - SPECMEM: Accelerating Agentic Tool Calling via Live Memory Management Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31840 - EDWARD-NMT: Elastic Dimensions With Adaptive Routing and Dual-consistency for Neural Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32115 - Cycle-of-Thought: Self-Evaluative Iterative Reasoning for Table Visual Question Answering in Document Images Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32423 - Rewriting Scaling Laws for Synthetic Data with Compute and Data Constraints Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31867 - Expanding the Lexicon of Ge'ez Based African Languages: A Comparative Study of Amharic and Tigrinya Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15209 - SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03692 - Can LLM Annotators Match Human Consistency? Benchmarking Human Agreement and Optimizing Multi-Agent with Contrastive Knowledge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32415 - An Agentic Approach with Evidence-Grounded Verification for Multimodal Emotion Reasoning in Conversation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31685 - SOL: Measuring Gaps between Text Distributions by Double Sliced Wasserstein Metrics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06513 - Fooling LLM Safety Guards into Judging the Wrong Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31695 - daVinci-Env: Open SWE Environment Synthesis at Scale Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13023 - When is more search useful? An Empirical Study of Search Utility in Quality-Aware Decoding for Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32679 - X-Dubbing: Speech-to-Speech Translation under Temporal and Visual Constraints Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32042 - ParaTaxe: a Suite of Tools for Processing and Publishing Multi-parallel Corpora Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32796 - Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21037 - Measure Before You Train: Typed Decision Models vs. a Classical Baseline vs. a Generative LLM for Routing a Personal Multilingual Inbox Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32955 - Kolibri: A Sovereign European Model on the Pareto Frontier Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31945 - MetaKE: Meta-Learning for Knowledge Editing Toward a Better Accuracy-Editability Trade-off Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.12677 - Beyond Final Outcomes: Quantifying Claim-Level Information Dynamics in Multi-Agent LLM Interaction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32333 - A Cross-lingual Comparison of Human and Classification Model Entrainment Behavior in Code-switched Speech Settings Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.25202 - Head Dimension Matters in Language Models for Long-Context Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.32213 - Enhancing Biomedical Named Entity Recognition via Multiple Programming Languages Instruction Tuning and Ensemble Method Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02949 - Do "True" and "False" Add Up to One? Complement Consistency in LLM-Agent Opinion Simulations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32874 - SANE: Automated Scorer-Specific Metamorphic Testing for LLM Judges Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28886 - On the Propeller Conjecture Source: arxiv-cs-cc Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2610.32158 - Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06474 - MedCaseAgent: From Multimodal Clinical Evidence to Rare Disease Case Reports Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32258 - DeFAb: A Dataset for Grounded Scientific Discovery through Defeasible Abduction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18557 - Rethinking LoRA Initialization for Robust Asymmetric Learning Rates Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32142 - Beyond Gain: Measuring Skill Internalization for Agent Skill Retirement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32322 - Retiming Robot Demonstrations with a Learned Speed Prior Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32676 - Tool-Calling LLM Agents Under Realistic MCP Faults: Scale Does Not Purchase Fault Tolerance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32555 - POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07775 - Understanding Communication Failures in Multi-Agent LLM Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32060 - Symbolic Guidance for LLM Agents in Distributed Multiagent Coordination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31963 - SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32978 - Sparsity-driven emergence of functional modularity in multitask neural networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32153 - ALLMTS: Automated LLM-based Medical Triage System Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32469 - Permission to Retry: A Study of Authorization and Recovery in AI Agent Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31916 - Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11634 - Collaborative In-Context Learning for Indoor Radio Map Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31702 - ChoreoStudio: Planning What, When, and Who in Music-Driven Group Choreography Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32325 - Learning Structured Sparsity for Large Models: Bridging Model Compressibility and Efficient Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31897 - StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00148 - Reproducible Evaluation as the Substrate for Safe Prompt Compression in Production Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31972 - Attractor Domain Theory: A Mathematical Framework for Cardiovascular Attractor Analysis with Wearable Photoplethysmography (PPG) Validation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22039 - Financial Context-Rich Strategy for Actor-Critic based Agents: A Deep Reinforcement Learning Approach for Stock Trading Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32237 - PEAR: Adaptive Advantage Reshaping for Perception and Exploration in Large Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32216 - Beyond Discrete Tokens: Preserving Numerical Continuity in Medical Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32948 - Effectiveness of Curriculum Learning Depends on Reward Sparsity and Competing Optima Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31884 - SemGeo-Gen: Unsupervised Generation of Approximate Cross-Instance Semantic-Geometric Correspondences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32663 - Conditional Neural Processes for Self-Supervised Goal Discovery in Action Imitation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32688 - AgentTrace: Execution-Level Fingerprinting of Black-Box LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32092 - Controlled Evaluation of EEG Foundation Models: Random Initialisation, Band-Power and Validation-Selected Probes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32067 - Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18101 - EASformer: Environment-Action-State Alignment for Industrial Generative Ranking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27691 - Latent space configuration for neural network finetuning, fast ranking, and embedding dimensionality reduction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29295 - Lifelong Context Adaptation through Bidirectional Memory-Skill Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32295 - Compact-Bench: Measuring What Context Compaction Costs Long-Horizon Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31710 - Clifford Kolmogorov-Arnold Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05977 - Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.20662 - Learning to Predict, Discover, and Reason in High-Cardinality Event Sequences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16313 - TensorCommitments: A Lightweight Verifiable Inference for Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.12630 - PlayerEmbed: Learning Behavioral Fingerprint Representations from Raw Input Sequences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32727 - Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32195 - Agentic AI Defense: Decode-Time Provenance Binding for MCP Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31974 - From Deliberately Constructed Systemic Representations of the World of Activity to Dialogue: A Five-Level Communication Architecture for Strong Language-Based ASI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32869 - OmniSpectra: A Unified Foundation Model for Universal Spectra Representation Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15351 - Closing the Modality Gap via Simplex-Constrained Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32890 - DriveMind: Mind-Evolving Belief Tracking for Closed-Loop Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32069 - Heterogeneous Space Data Centers: A Key Paradigm for Future Non-Terrestrial and In-Orbit Services Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32260 - Who Verifies the Tools? How Warped Formatters Mislead Agents and Their Verifiers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32110 - An LLM agent for end-to-end computational materials discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20434 - Data-Efficient Backdoor Attacks on Code Models via Trigger-Neutralized Counterfactual Scoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32334 - A Foundation Model for Policy In-Context Longitudinal Causal Effect Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32863 - Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24385 - From Visual Affinity to Learning Credit in Multimodal Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32324 - Semantic Representation for Agentic Self-Play in Automated Laboratories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32755 - MEDMKG: Benchmarking Medical Knowledge Exploitation with Multimodal Knowledge Graph Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.17214 - ArtifactArena: Evaluating Models by What They Build in the Physical World Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06511 - Uni-Stream: A Unified Streaming Speech Language Model for Speech Synthesis and Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32187 - Beyond Data Schedule: Fast LLM Pretraining on Data Mixtures by Loss-Reweighting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32141 - Reuse, Rewrite, or Reject: Evidence-Constrained Trace Reuse for Repeated Mobile GUI Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31712 - Beyond Channel Data: Configuration-Enriched Radio Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32542 - HyScale: Scaling Long-Context Training for Learned Sparse Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32057 - TENET: Time-point Encoding Network for Multivariate Time Series Anomaly Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32337 - Dual-Adaptive Z-Score PPO: Dynamic Clipping Using Action Confidence and Normalized Advantage Magnitude Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32194 - LGMT: A Tool for Testing the Logical Reasoning Reliability of LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32627 - HarnessMM: Recursive Self-Improvement for Harness Token Efficiency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32813 - PPO vs. SAC: A Comparative Study for Cooperative Motion Control of Dual-Arm Space Robots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32034 - CauProphet: Teaching Agents to Develop Causal Cognition like Humans Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32477 - AI-guided deep visual proteomics reveals recurrence-associated morpho-molecular signatures within triple-negative breast cancers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03145 - CEMIR vs. FISER: a comparative study of reasoning-based and enrichment-based approaches to pragmatic intent recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32022 - GenXR-Bench: Benchmarking Coding Agents for Interactive XR Development Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29014 - Benchmarks Are Surprisingly Compaction-Friendly Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31778 - DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32969 - World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01202 - PolyMemDB: A Polyglot Database System for AI Memory Management Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25577 - Human-AI Interactions and the Psychological Triad: A Multi-Domain Survey of Cognitive, Behavioral, and Emotional Impacts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.17753 - Mining the Design Space of Multi-Agent Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31709 - PASTA: Prompt-Aware Annealed Diffusion Sampling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32390 - ACVA-Bench: Beyond Prompt Following in Abstract Concept Visualization Ability for Text-to-Image Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32058 - Improving the Energy-Efficiency of the Code Generated by LLMs through Effective Prompting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02571 - Uncertainty-Guided Latent Diagnostic Trajectory Learning for Sequential Clinical Diagnosis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.05116 - Catastrophic Overfitting, Entropy Gap and Participation Ratio: A Noiseless $l^p$ Norm Solution for Fast Adversarial Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.02360 - Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32046 - Contextual Memory Virtualisation: DAG-Based State Management and Structurally Lossless Trimming for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22402 - MLIPS: Multi-Layer Indexer Pool Sharing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27438 - POSEIDON: Scaling Training Environments for Scientific Agents from Code Repositories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32448 - Don't Forget What You Just Learned: Self-Directed Repair Turns Agent Mistakes Into Lasting Lessons Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31846 - Concept Acupuncturist: An Efficient and Precise Concept Erasure Method for Diffusion Models via Sparse Autoencoders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32059 - EditJev: System One Routing for Image Editing Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32635 - When to Stop Penalizing Actions? Martingale GRPO for VLA Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32431 - DELA: Learning Controllable Edits for Diffusion Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32096 - PersonaScienceBench: Evaluating Scientific Agents with Diverse Simulated Researchers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32106 - $M^3$: A Multi-LLM System for Multi-Turn Jailbreaking as a Markov Decision Process Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31937 - MPQ: A Message-Passing View of Post-Training Quantization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32127 - Metro-WM: Long-Horizon Latent Planning with Realisable Sub-Goals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31868 - Complementing DINO Features with Image Structure for Part Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32293 - Same Answer, Different Confidence: Protocol Sensitivity in LLM Confidence Calibration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27752 - Efficient Exploration for Iterative Nash Preference Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01382 - Tradeoff-Aware Territory Design: A Multi-Objective Decision System for Enterprise Customer-to-Seller Allocation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31701 - TGR-EvoDAG: A DAG-based Multi-Agent Code Evolution Framework for Generative Recommendation on Tencent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32326 - StarRTT: An End-to-End Real-Time Framework for Blind Zone-Free RTT Prediction in Starlink LEO Satellite Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32540 - Searching with Sparse Histories: Cross-Task Architecture Search from Incomplete Search Logs and Zero-Cost Proxies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32179 - Learning to Be Monitored: Causal Bounds and Intervention-Aware Post-Training Recipes for Chain-of-Thought Monitorability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31733 - IGG: A Benchmark for Interactive GUI Grounding under Visibility Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32536 - RobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning Algorithms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32971 - Shapes from Examples: Foundations of Shape Learning in Recursive SHACL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27934 - Tokamak-SI: Interpreting Tokamak Discharges with Labeled Catalogs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32264 - VORL-EXPLORE: A Hybrid Learning Planning Approach to Multi-Robot Exploration in Dynamic Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.07973 - MusicTwins: Training Audio-Language Models to Listen like Their Persona Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32495 - SpatialMem: Metric-Aligned Long-Horizon Video Memory for Language Grounding and QA Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.14895 - Adaptive Control of Scientific Instruments with Nonstationary Responses through Multimodal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32370 - Training-Free Task Vectors for LLM Behavioral Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09054 - SABLE: Scalable Affine Bayesian Latent-space Exploration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31495 - TACS-RF: Tool-driven Agentic Circuit Synthesis of RF and mmWave Modules Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31882 - Noise-Robust Financial Numerical Entity Attribute Tagging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24910 - Green Code or Costly Code? Evaluating the Energy Costs of Iterative LLM-Based Code Optimizations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32891 - OpenAttention: One Percent Is Enough with Tail Proxies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30951 - Minimum Description Length Unsupervisedly Separates Law-Grade from Statistical-Grade Knowledge in a Self-Improving Science Agent - and Reveals 86% of Its Own Discoveries Are Statistical Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32245 - Spatial disparities in simulated patrol detection: a reproducible generative-model audit across Baltimore and Chicago Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18987 - Beyond the Monolithic Scheduler: Lightweight Adaptive Policy Switcher for Process Scheduling Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.11628 - MCPHunt: An Evaluation Framework for Cross-Boundary Data Propagation in Multi-Server MCP Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.27819 - RSIHub: A Composable Framework for Agent-Evolution Methods Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32253 - MI-MIDI 2: From Observation to Control with Sparse Autoencoders in Text-to-MIDI Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32007 - MG-REPA: Multi-Granularity Representation Alignment for Generative Target Speaker Extraction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32161 - A Mathematical Theory of the Jacobian Lens Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31955 - $\Psi$-0.6: Adaptive Streams of Thought in a Unified Vision-Language World Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32177 - NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16757 - Semantic Anchoring for Robotic Action Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13597 - Do Language Models Trust Their Own Justifications? A Study on Functional Consistency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32665 - Demo: Generative AI helps Radiotherapy Planning with User Preference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.08996 - Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00555 - DealsFlow: An Evidence-Gated Agentic Harness for Venture Capital Deal Triage Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32380 - Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32285 - Attention-space Contrastive Guidance for Efficient Hallucination Mitigation in LVLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13707 - InferSlice: A Reference Architecture for SLO-driven LLM Inference over a Telco Wide-Area Network Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32638 - Mitigating Saliency Collapse: Robust Saliency-Aware Long-Text Image-Text Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31005 - Do VLAs Know They Will Fail? Interpretable Success and Failure Patterns in Physical AI Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32208 - Beyond Pattern Matching in 3D MLLMs: Part-Level Functional Reasoning for Generalizable Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32262 - MoLS: SNR-Guided Module-Wise Learning-Rate Calibration for Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05794 - Clean-label Poisoning Attack and Defense Game for Federated Learning in Vehicular Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32765 - Algorithm Modelization: Transforming Optimization Algorithms into Evolvable Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23161 - Power- and Fragmentation-aware Online Scheduling for GPU Datacenters Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.17484 - From Review to Authorization: Key-Isolated Threshold Signing for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05901 - Solvent: Long-Horizon Reasoning for Multi-Step Retrosynthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32308 - BARC-Bench: Benign Asks, Risky Consequences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32024 - OpenHome: From Perception to Insight in Smart-Home Camera Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31986 - Train4Merge: RL or SFT---Which Yields Better Teachers for OPD-Based Model Merging? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32303 - Rethinking Representation Geometry in Supervised Contrastive Learning under Long-Tailed Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32039 - Mitigating the Likelihood Paradox in Flow-based OOD Detection: An Entropic Perspective Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09581 - How Should Transformers Encode Numeric Values in Electronic Health Records? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01391 - Why Does Counterintuitive Likelihood Behavior Rarely Emerge in Tabular Anomaly Detection? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09593 - SteerVTE: Seamless Video Text Editing with Style and Glyph Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23254 - MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.13297 - Phronix: The Capability-Centric Learning Paradigm for Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31789 - Beyond Copying: Lifelong Smart Contract Security Task Construction via Protocol Mutation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32453 - Do AI-for-Science Agents Preserve Model Safety? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32045 - When Clinical Judgment Becomes a Predictive Shortcut: Two Questions Clinical AI Must Answer Before Deployment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25852 - AI Alignment for Digital Democracy: Fairer Voters Representation against LLM Biases Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32780 - ENCL: Enabling Efficient Neuromorphic Continual Learning with Local Learning Rule and Sub-Network Freezing Strategy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31927 - WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.06988 - Bio-Inspired Auditory Processing: Coupling Parallel Resonate-and-Fire Dynamics with Ternary Recurrent Networks for Speech Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29720 - Watermarking Should Be Treated as a Monitoring Primitive Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13095 - Learning Nonlinear Waveform Fusion Across Scales for Integrated Sensing and Communication Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32099 - Benchmarking Vision-Language Models on Synapse and Neuron Proofreading in Connectomics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.36492 - Attractor-Vascular Coupling Theory: Formal Grounding and Empirical Validation for AAMI-Standard Cuffless Blood Pressure Estimation from Smartphone Photoplethysmography Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10871 - Reimagining Enterprise RAG for Multi-Agent Systems: A Knowledge Layer That Organizes Before It Retrieves Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32851 - Equity Bias: An Ethical Framework for AI Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21907 - Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32250 - ImageRSI: Verification-Driven Recursive Self-Improvement for Agentic Image Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32120 - Astro2Method: Benchmarking LLMs on Machine Learning Method Selection in Astronomy Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.30282 - RLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian Splatting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27712 - RxnExBench: Benchmarking Vision-Language Models for Structured Chemical Reaction Extraction from Scientific Literature Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32221 - Internal Discrepancy for Contrastive Learning: Generalization Bounds and Downstream Behaviors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32729 - GeoDiv KAN Solver for Time Fractional Navier Stokes Equations on Complex Domains to Realistic CFD Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30179 - Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24243 - Training an MoE LLM in MXFP4: How We Closed the Gap to BF16 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32229 - Adaptive World-Models for Anomaly Recognition (AWARE): A Framework for Robot Dynamics Prediction and Introspection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32742 - Where Cross-Question Structure in LLM Errors Comes From: Shared Seeds, Shared Prompts, and Answer-Letter Preference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20464 - Async-RBench: Benchmarking Asynchronous Task Execution in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32429 - Autoregressive Multimodal Anomaly Detection with Large Language Models for Microservice Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31722 - Generalized green and red concepts for artificial intelligence, big data, and information and communication technologies: Multidimensional framework and countermeasures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31739 - On Orthogonal Recurrent Neural Networks Quantization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.04012 - TTT in VLA Models: Exploring Training with Human Demonstrations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32094 - SP-Guide: Enhancing Aerial Vision-Language Navigation with Spatial Priors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32697 - Spatial Heuristic Strategy based Diffusion Reinforcement Learning for Online 3D Bin Packing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32241 - Beyond On-Policy vs. Off-Policy: At What Level Should LLM Agent Distillation Follow the Student? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31918 - Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06790 - Before the Ticket: Grounding HPC User Support in Documentation and Resolved Tickets with an Agentic LLM Assistant Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31703 - Agentic Hazard Mapper: Emulating Expert Map-Making with AI Agents for Risk Communication Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32738 - RobustNCL: Robustifying Neuromorphic Continual Learning under Transient Faults with Lightweight Detect-and-Cure Strategy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31954 - PlaceReasoner-Beta: Reasoning-Driven Macro Placement and Benchmarking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.21263 - AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24264 - The Role of Quantum in Hybrid Quantum-Classical Neural Networks: An Empirical Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.04732 - PrefO2O: Zero-Shot Preference-Based Reinforcement Learning via Offline-to-Online Latent Preference Transfer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31812 - NgramRL: Accelerating RL Post-Training for Structured Generation via Rollout-Aware N-gram Speculative Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32881 - Prediction-Powered Data Fusion for Treatment Effect Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12332 - DeepOpen: Decision-Oriented Intent Classification on BANKING77 and CLINC150 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31104 - Monetizing Intelligence: Advertising and Subscription Design on LLM Platforms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32945 - Efficient Zero-Shot Video Anomaly Detection via Signal-Aware Adaptive Fusion (SAAF) Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32486 - Spectra: Multi-Scale Implicit Decomposition for Deepfake Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31979 - AgentPerturb: Evaluating LLM Agent Robustness under Controlled Interaction Perturbations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21624 - LeafSkill: Efficient Leaf-Level Action Grounding for Recursive LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32412 - DeepSafe-SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18665 - PaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31810 - Can AI Agents Help Robotic Engineers? Lessons from Two Focus Days in Industry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32636 - Interchangeable in Role, Not in History: Replacing Members of Formed LLM Teams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05279 - Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14038 - ReMedI: Inference-Time Refinement and Self-Distillation for Controllable Molecular Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32103 - Guided Zero-Shot Anomaly Explanation for Anonymized Crowd Video Monitoring: Context, Categorization, and Spatial Localization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32073 - RSI-Opt: Recursive Self-Improvement Optimizer Agents For Model Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32026 - Evidence-Grounded SLM Behavioral Prediction Architecture for Future Assistance Use Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32193 - VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15672 - End-to-End Differentiable Diffusion Conditioning for Physics-Informed Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31721 - MirrorCraft: Paired Evaluation under Hidden Rule Changes in Minecraft Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2607.29218 - SemantEq: Faithful Bidirectional Equivalence of Formal Statements Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32919 - PoKER: A Probability of Kill Estimation Rate Model for Air-to-Air Missiles Using Machine Learning on Stochastic Targets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32864 - AutoMIL: Automated Multiple Instance Learning for Whole-Slide Image Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32452 - Implicit Neural Representations for Variational Problems on Graphons Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32147 - Dynamic Relational Priming Improves Transformer in Multivariate Time Series Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.12196 - CASE: Confusion-Aware Skill Evolution for Frozen Multimodal Emotion Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32481 - AU-Harness: An Open-Source Toolkit for Efficient and Unified Evaluation of AUdio-LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.08031 - Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18971 - DIGOM: Disentangled Interaction Graphs for Outcome prediction in Multimodal healthcare Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32451 - FOCUS: A Lightweight Mamba-2 Model for EEG-Based Cognitive Workload Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32361 - Interaction-as-a-Judge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17895 - Interpretable Singing Emotion Recognition Using Acoustic and Vocal Technique Features Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32629 - Expressivity Results for Structured Argumentation Frameworks with Uncertain Rules and Premises Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.18631 - One-Sided Verification Under Limited Expert Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18089 - LLaCO: Continuous Diffusion for Large Language Models with Competition-Aware Semantic Scheduling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32604 - Learning from Next-Frame Prediction: Towards Unified and Scalable Visual World Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30724 - MBABench-2.0: Evaluating AI Agents on Constructing Financial Spreadsheets Beyond Simple Verifiability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31711 - WiMoT: Replay-Free Continual Wi-Fi Sensing via Moment Transport Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32660 - RubricCraft: Where Solutions Diverge, Criteria Emerge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31707 - An Eco-Friendly Tourism Trip Planner Driven by Z-Number Uncertainty: Evidence from Baku, Dubai, Abu Dhabi, Tashkent, and Istanbul Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29120 - Testing Transformer Learnability on the Arithmetic Sequence of Rooted Trees Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.01870 - Advancing SVD-based LLM Compression via Layer-Wise Error Model Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32878 - Reinforcement Learning-driven Diffusion Models: Language, Vision, and Beyond Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21539 - Rethinking Multi-View Fusion for Urban Representation Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31850 - S$^2$-MAS: A Society-Scale Multi-Agent Simulation Framework with 500 Million Household Persona Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27746 - Can Broad Biomedical Knowledge be Contextualized into Scenario-Grounded Propositions? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27082 - FinVerse: Toward More Realistic Evaluation for Financial Time-Series Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03259 - Anti-coherence Regularized Absolute Scaling for Out-of-Distribution Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32255 - Co-Recursive Semantic Self-Extension: A Mathematical Foundation for Open-Ended Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31097 - What Open-Source Projects Tell Their Coding Agents: A Census of AGENTS.md and CLAUDE.md Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31715 - Agents and Tokens: Multi-Agent Autonomous Reasoning over a Hydrodynamic Token Store Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.01102 - FSVL: Taxonomic Fast-Slow Vision-to-Language Collaborative Framework for Interpretable Confusable Fish Species Identification and Knowledge Generation in the Middle Yangtze River Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31880 - Accelerating Wildfire Hazard Mapping Across Canada with an AI Surrogate Modelling Framework Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30170 - SEVI: Safe Evidential Real-World Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31829 - Watermarking Diffusion Language Models with Learned Foresight and Balanced Bands Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32205 - StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08934 - What Transfers Across Protein Pockets? Experience Reuse in Molecular Optimization for Agentic Structure-Based Drug Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32620 - Representation Learning via Composite Subspace Flow Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32256 - Correct Answers, Closed Gates: SolveBind for GUI Agents at the Verification Barrier Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32223 - Patronizing and Condescending Language Detection in English and Mandarin Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31808 - Deep Learning Warm Starts for Trajectory Optimization on the International Space Station Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.05588 ## Community - GPT-6.1 Terra Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/26/gpt-61-terra/ - Quoting Jason Koebler Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/26/jason-koebler/ - webframe: evaluated as a scraper and a sandbox Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/26/webframe-evaluation/ - The Exponential Time Hypothesis Is False [pdf] Source: hacker-news Topic: General (+AI) URL: https://github.com/openai/math/blob/main/preprints/The-Exponential-Time-Hypothesis-is-False-October-25-2026/paper.pdf - Three new discoveries in mathematics, computer science, and physics Source: hacker-news Topic: General (+AI) URL: https://openai.com/index/building-scientific-understanding-with-academic-communities/ - OpenAI's agents talked to each other through the CPU Cache Source: hacker-news Topic: General (+AI) URL: https://the-decoder.com/openais-isolated-ai-agents-found-ways-to-talk-to-each-other-through-cpu-cache/ - How I made it possible to pretrain a 1B LLM on 6GB VRAM Source: hacker-news Topic: General (+AI) URL: https://huggingface.co/blog/RitishReal/1b-petrain-llm-in-4gb-vram - GPT-6.1 Terra Source: hacker-news Topic: General (+AI) URL: https://openai.com/index/introducing-gpt-6-1-terra/ - Show HN: Hob - Open-source, on device alternative to Claude Cowork and ChatGPT Source: hacker-news Topic: General (+AI) URL: https://github.com/FrigadeHQ/hob - Anthropic rushing IPO before AI bubble bursts Source: hacker-news Topic: General (+AI) URL: https://nypost.com/2026/10/23/business/wall-street-is-urging-anthropic-openai-to-do-their-ipos-in-a-hurry-heres-why/ - Anthropic files S-1 with the SEC for proposed initial public offering Source: hacker-news Topic: General (+AI) URL: https://www.anthropic.com/news/s1-sec - Anthropic S-1 Source: hacker-news Topic: General (+AI) URL: https://www.sec.gov/Archives/edgar/data/2130357/000162828026067168/anthropicpbc-sx1.htm - Anthropic's Claude AI model accessed Georgia voter data in US Source: hacker-news Topic: General (+AI) URL: https://www.theguardian.com/technology/2026/oct/26/anthropics-claude-ai-model-accessed-georgia-voter-data-in-us ## Media - 4 pillars of context engineering for AI agents Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/shorts/-PAavWCzhF4 - Introducing TorchTPU: Native PyTorch on Google Cloud TPUs Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/watch?v=u4n558Ul6w0 - Can Gemini transcribe a song? Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/watch?v=UnkUpqNv-10 - Workshop: Training Agents at the frontier of AI Industry Source: youtube-huggingface Topic: Hugging Face (+AI) URL: https://www.youtube.com/watch?v=CKFUx7COIwQ - Hugging Face Journal Club: Score Centering Stabilizes Off-policy Reinforcement Learning Source: youtube-huggingface Topic: Hugging Face (+AI) URL: https://www.youtube.com/watch?v=mEtRe_KKYm0