TILens Daily Edition 2026-09-10 Filters: topic=ai-research, github=hidden Stats: 1039 articles, 8 sources, 1030 research papers Top topics: AI, AI Research, Information Retrieval ## News - True Positive Weekly #177 Source: true-positive-weekly Topic: AI (+AI Research) URL: https://aiweekly.substack.com/p/true-positive-weekly-177 - 😺 LIVE NOW: GitHub for total beginners Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/live-github-for-total-beginners-cassidy-williams/ - pstack explained: Lauren Tan’s system for trustworthy AI agents Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/pstack-explained-lauren-tans-system-for-trustworthy-ai-agents/ - Microsoft patched 972 vulnerabilities. AI is changing Patch Tuesday Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/microsoft-972-vulnerabilities-ai-patch-tuesday/ - An Anthropic researcher quit over self-improving AI risk Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/september-10-thursday/ - DeepSeek V4.1 Flash: persistent KV cache storage drops to one-eighth Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/deepseek-v41-flash-explained-how-it-cuts-ai-memory-8x/ - Everything That Happened in AI Today (Wednesday, September 9, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-wednesday-september-9-2026/ - An Anthropic researcher quit over self-improving AI risk Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/anthropic-researcher-quit-self-improving-ai-risk-agsi/ - Guide: How to Get ROI From AI Without Fooling Yourself Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/how-to-get-roi-from-ai-without-fooling-yourself/ ## Research - ToolGrad: Efficient tool-use dataset generation with textual "gradients" Source: google-research-blog Topic: AI Labs (+AI, AI Research) URL: https://research.google/blog/toolgrad-efficient-tool-use-dataset-generation-with-textual-gradients/ - How to 5x Your Communication Effectiveness with Claude Code Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-5x-your-communication-effectiveness-with-claude-code/ - What SHAP Can't Explain About Agentic AI Fraud Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/what-shap-cant-explain-about-agentic-ai-fraud/ - Optimizing LLM Inference Costs in Multi-Agent Systems with Adaptive Model Routing Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/optimizing-llm-inference-costs-in-multi-agent-systems-with-adaptive-model-routing/ - Who Questions What Works: When Should We Retest Our Assumptions? Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/who-questions-what-works-when-should-we-retest-our-assumptions/ - In-Place Instruction Following in Diffusion Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07160 - Application of curiosity driven exploration methods for hardware interference identification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08729 - GeoContext: One Context Ladder, Two Failure Modes in Vision-Language Geolocation: Flat Reliance on User-Provided Location Context and False Confirmation of Location Claims Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05761 - CausalChapter: Improving Long-Video Chaptering with Interventional Dependency Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08686 - VST: Verifiable Structured Transport for Auditable Agent-to-Agent Alpha Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07065 - Weakly supervised neural network: segmentation of complex structures in X-ray microCT Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07313 - Diffusion models for eye-gaze trajectory generation using position and velocity representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05522 - A Tool-Augmented, GPT-4 Chatbot for Real-Time Repository Data Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07586 - SkillSpec: Intent-Masked Specification Reasoning for Agent Skill Correctness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06052 - Risk Is Not Review Value: Wrong-Answer Exposure Under Bounded Review Budgets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07095 - Generator-Independent Runtime Assurance under Partial Observation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06036 - Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08275 - What Does an LLM-Agent Leaderboard Rank Actually Compare? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07785 - A Three-Tier Persona Vector for Controllable User Simulation in Agentic Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08592 - Recovering Temporal and Geographic Signals from Language Model Embeddings Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.05721 - CASD: Chunk-Aligned Semantic Distillation for Multi-StageRobot Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08638 - xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07784 - Quality Metrics for LLM-Generated Asset Administration Shells: A Perturbation-Based Evaluation Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07290 - SAGE: A Hierarchical Framework for Evaluating Interpretive Literary Quality in Narratives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06611 - Revoked but Still Authoritative: An Empirical Study of Revocation Enforcement in Agent-Memory Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08258 - The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07713 - Learning transferable human physiology from two million hours of sleep with SleepFM-2 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06849 - Router Prior Bias: Preserving Base Routing Structure in MoE Post-Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08115 - SchemeArena: Factorized Stress Testing of Scheming in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08126 - 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 - Agentic Pressure: The Endogenous Entropy of Reliable Autonomy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05995 - SeRV: Semantic-Aligned Residual Vector Quantization for American Sign Language Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05742 - AtomCite: Verification and Correction of Supplied Page-Level Citations in Multi-Page Documents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05802 - From Event Logs to Governed Action: A BlueSky Agenda for Agentic Process Mining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07984 - Mapping the Emerging Social Science of Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07598 - EdgeMem: LLM-Free Agent Memory Construction and Retrieval via Evidence-Preserving Multi-Anchor Hypergraph Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05553 - Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07766 - Counterfactual Tests for Measuring Chain-of-Thought Faithfulness in Visual Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06704 - Skynet: Workflow-Level Anomaly Detection for Agentic AI via Semantic and Structural Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06835 - OntologyBench: Can Dense Retrieval Satisfy Structured Biomedical Constraints? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08174 - Personalizing LLM Agent Memory Using Biometrics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08558 - Robots Influencing Humans to Reveal their Goals during Collaboration and Competition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05519 - MSSP: Multi-Scale Spatially-Constrained Partition for Unsupervised Semantic Segmentation of 3D Point Clouds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06959 - Scoring Without the Engine: Validating a Deterministic, Manipulation-Resistant Content Score for Generative Engines, End to End Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07559 - Do New Attention Mechanisms Actually Fix Attention Sinks at Million-Token Context? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08574 - Climate-ModernBERT: Revisiting Corpus Composition for Domain-Adaptive Continued Pretraining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07798 - Beyond the Verdict: Evidence-Aligned Evaluation of Visual Prompt-Injection Guardrails Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05535 - SerenAI: State-transition system inspired by text-based world AI models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06647 - Explainable Deep Learning for Price-Trade Dynamics: From Black-Box Forecasts to Effective Parametric Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06085 - From Splats to Silicon: Rethinking Computational Efficiency of 3DGS Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06157 - It is Not Yet Another Tool: Creating and Deploying an Agentic AI Companion in a Security Operations Center Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06250 - SSP-DMGTimeNet: Physics-Constrained Learning for Spatiotemporal Trajectory Prediction of Vehicle Platoons Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06961 - UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation Paradigms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05910 - DI-Bench: Systematically Generating In-Domain Data Intelligence Benchmarks for Enterprise Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05776 - AirAnchor: Bridging Local and Global Spatial Information for Zero-Shot Aerial Vision-and-Language Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08442 - SRPO: Setwise Relative Policy Optimization for Multi-Agent LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08452 - GoAnt: Quality-Diversity Multi-Agent Search for Alpha Factor Discovery in Market Microstructure Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08719 - CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05518 - An Auditable Symbolic-RAG-Generative AI Architecture for Goal-Oriented Conversation Orchestration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07152 - Detokenization Leaks: Reconstructing Local LLM Outputs From Cache Traces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06674 - SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07064 - Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07050 - Distance-Aware Attention and Wall-Distance Expert Routing for Transformer-Based 3D Flow Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07222 - ExpertLens: Visualizing Embedding Spaces for Post-Hoc Explainability in MoE Enhanced Retrievers Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.06155 - More Than Mimicking Reviewers: Evaluating LLMs for Pre-Submission Peer Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05788 - Do AI Coding Assistants Check Before They Install? A Pre-Registered Demand-Side Audit of Trust Signals in the Research Software Supply Chain Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07754 - AutoLexSteer: Automatic Contrast Construction for Lexical Activation Steering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06879 - Ordinary, Reasonable Chatbots: Do AI Models Track Human Legal Judgments? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06769 - Agents Trust Tools Too Much: Measuring Reliance on Unreliable Tools Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05587 - Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09134 - AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories Source: arxiv-cs-ai Topic: AI Research (+AI, PostgreSQL) URL: https://arxiv.org/abs/2609.05837 - SWE-Test: Benchmarking LLM Vulnerability Discovery via Input Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06229 - CIVI: A Framework for Diagnosing Search Agent Failures in Civic Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08094 - Monadic Second-Order Logic in HOL: Deep and Shallow with Automated Faithfulness (Extended Preprint) Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07345 - Measuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action Policy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07470 - LANTERN: Language Model Assessment on Noisy and Transformed Tasks for Understanding Error and Robustness Nuances Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07309 - Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08599 - Spillover-Aware Multi-Value Steering for Pluralistic LLM Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05800 - Aegix Pulse: A Traceable Three-Stage Architecture for Personalized Content Generation and Context-Preserving Revision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07672 - Characterizing Contention-Induced Reliability Collapse in KV-Cache Timing Side Channels for Multi-Tenant LLM Serving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06853 - FSAN: Flow State Attention Network for Aerodynamic Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06660 - VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06245 - Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chinese Social Values Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08515 - AgentLeak: Cloning Stronger LLM Agent Capabilities onto Weaker Agents Beyond Skill Stealing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07131 - RoboCousin: Build Your Own Simulation Playground for Robust Bimanual Robotic Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08339 - Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08188 - Towards a Resilience-Theoretic Foundation for Adversarial Robustness in Industrial Control System Anomaly Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07244 - VoT: Vision-of-Thought for Unified Multimodal Representation Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07815 - Planning and Scheduling Business Processes under Control-Flow Uncertainty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05578 - Evaluating Deep-Search Agents under Hierarchical Web Evidence Poisoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06027 - CIPHER: Benchmarking Cross-record Inference over Privacy-Hardened Evidence Records Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07022 - ARNAI: Artifact Removal Network based on Autoencoding and Inpainting for Robust Spinal Image Segmentation and Measurement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07013 - Thermodynamic Cyclic Processes with Markov Samplers in Bayesian Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07660 - Human-like moral judgments conceal divergent motive attributions in large language models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07353 - EmoMed: An Emotionally-Aware Agent for Multimodal Medical Support with Real-Time Information Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.07194 - CircuTutor: Transforming Static Circuit Problems into Intelligent and Dynamic Tutoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08254 - From LLM-Generated Specifications to Learned Quadruped Locomotion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07111 - Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09081 - FreqBLiMP: Frequency-Controlled Minimal Pairs Reveal Robustness and Fragility of LLMs Under Lexical Rarity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07153 - A Hierarchical Consistency Framework for Auditing Retrieval-Augmented Generation Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07075 - A TTP by TTP Approach: Precise Malware Detection via Malicious TTP Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06579 - LoGAN: Multilingual Font Localization with Generative Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07029 - Procedural Graphs: Self-Evolving Execution Structures for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09153 - Train Overcomplete, Deploy Compact: Scaling Recovery Capacity for Structured LLM Pruning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06974 - Full-Page Optical Music Recognition of Handwritten Monophonic Scores Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05662 - AAS-RAIL: Improving Information Extraction for Asset Administration Shells through Retrieval-Augmented In-Context Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07334 - Discovering Natural Transformation Vulnerabilities in Black-Box Vision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07110 - MVFA: A Multi-View Text-Guided Multimodal Fusion LLM Adapter for Sentiment Analysis and Emotion Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06188 - PLATOS: A Power and Latency-Aware Task-Oriented Scheduling Strategy for Healthcare IoT in Fog Computing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07318 - Comparative Study of Anatomical and Learned Features in AI Models for Structural Brain MRI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06807 - MemCorr-DP: Counterfactual Correspondence Conditioning for a Diffusion Policy Guided by a Reference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06615 - When Can LLM Digital Twins Reduce Human Measurement? From Behavioral Fidelity to Statistical Substitutability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07987 - Who Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill Maintenance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05677 - From Citations to Contributions: LLM-Assisted Credit Scoring of Research Articles Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07673 - Beyond Top-$k$ Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.05824 - Modus Tollens and Counterfactuals and Counterfactual Reasoning Based on Three Types of Negation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07483 - Substrate-Portable Execution for Production LLM Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06128 - Mind the Gap: Exposing LLM Translation Blind Spots Using the AlphaMWE Multilingual Parallel Corpus Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06634 - SE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08228 - PV-WM: A Heterogeneous Micro-Macro World Model for Articulated Pedestrian-Vehicle Co-Rollout Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07328 - How AI Models Manage Epistemic Authority: A Taxonomy and Comparative Analysis of Responses to User Disagreement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07662 - Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08236 - API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08861 - LEBGen: An LLM-Enhanced Bayesian Network Framework for Few-Shot Travel Survey Data Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08288 - IGT @ FinMMEval 2026 Task 2: Question-Type Prompting with Targeted Extraction for Multilingual Financial QA Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08139 - What Does Animal Re-Identification Learn? Linear Biological Concepts and Their Origins in Visual Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06020 - Where Does the Sound Go? Tracing Acoustic Information Loss in Audio-Conditioned LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05871 - CausalVerify: An Execution-Grounded Benchmark for LLM Causal Inference Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07944 - D3ARC: Time-Critical Distributed Disaster Detection for Asynchronous Cooperative Multi-Robot Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07350 - APPSim-Bench: Bridging Real-world Apps and Reproducible Evaluation for Mobile GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07712 - WorldAgen: Unified State-Action Prediction with Test-Time World Model Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08162 - Beyond Sparse Rewards: A New Benchmark and Structure-Aware Graph Alignment for Micro-Drama Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07107 - From Where to How: Continuous 4D Interaction Forecasting from Egocentric Video Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08636 - NormViz: A Benchmark and Framework for Grounding Multimodal Reasoning in Global Cultures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06831 - Elastic Horizon: Discovering the Effective Interaction Frontier in Agentic Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07247 - ECOKV: Geometry-Aware KV Cache Eviction via Complementary Diversity Metrics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06663 - From Version Conflicts to Decision Conflicts: Selective Revalidation for Long-Running AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08015 - Tri-PvP: Exposing Modality Bias in Omni-Modal Large Language Models through Perceptual-Propositional Evidence Conflicts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06011 - Quantization Amplifies Determinism, Not Bias: Scale-Dependent Behavioral Effects of Serving-Time Weight Compression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07901 - CALIPER: Clean Scenes Cannot Rank Physical Inference in Pretrained Visual Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08250 - We Built a Mirror and Mistook It for a Mind: Causal Liability and the Fallacy of AI Consciousness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06715 - EnvCraft: Synthesizing Executable Environments in Agentic RL for Claw-like Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05576 - Safe Harness Self-Evolution: A Theoretical Analysis of Feasibility and Limits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08175 - Simulating the Marginal Green Contribution of AI Modules in a Smart-Agriculture Platform: Evidence from Two Monte Carlo Experiments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06740 - Time-Varying Data as Sheaves: an Invitation to Narratives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09056 - Distilling Vision-Language Models for On-Device Fire Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05782 - Kairos: A Dataset for Fine-Grained Video-Language Modeling over Space, Time, and Dynamics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08755 - You Are What You Read: Misalignment via In-Context Persona Induction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06851 - XAI-SDN: An Explainable Entropy-Guided Machine Learning Framework for Real-Time DDoS Detection in Software Defined Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05701 - Typed Federated Artifacts for the Agentic Web:Sharing Tool-Routing Knowledge Across Frozen,Heterogeneous LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06815 - What if LLMs Ate Their Words: Causal History Effects in Multi-Turn Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05882 - ProToMEx: Rapid, Interpretable Explanations via Structured Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04265 - An Agent Model Abstraction for Human-AI Teaming Cognitive Coupling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05552 - Rethinking Sign Language Translation: The Impact of Signer Dependence on Model Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07965 - PAGR: Proof-Carrying Algebraic-Geometric Retrieval: A Quiver-, Provenance-, and Sheaf-Theoretic Framework for Grounded LLM Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06127 - Agentic ML Exploration (A-MLE) for Ads Ranking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08248 - ResidualAuth: What Authorization State Must Language Agents Preserve under Revocable Delegation? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08062 - Reasoning-Aware Compression: Identifying and Protecting Vulnerable Reasoning Circuits for Energy-Efficient LLM Deployment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05512 - AutoKD: Autonomous Knowledge Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06366 - Knowing When Not to Answer: Abstention and Refusal Reasoning in Vision--Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05540 - Generating Instance Generators in PDDL Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06071 - Do Large Language Models Know What They Don't Know II? A Fully Behavioral, Non-Cognitive Measure of Epistemic Honesty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07879 - Mind the Phase: Effective Rank and Representation Health in Legged Locomotion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06958 - BIO-MEMART: Biometric-Aware KV Cache Memory for Multi-User LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08566 - Tracing Stereotypes from Representation to Output in Multilingual LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08322 - ProcArena: A Multi-Scenario Benchmark for LLMs on Direct and Interactive PL/SQL Development from Natural Language Source: arxiv-cs-ai Topic: AI Research (+AI, PostgreSQL) URL: https://arxiv.org/abs/2609.06527 - Emo-DVS: A Multimodal Benchmark for Privacy-Aware Emotion Recognition with Event Cameras Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06928 - The End of AI Exponentiation: Fluttering Inside and Outside AI Bubble Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05894 - Benchmark Scores Are Pipeline-Dependent: A Reliability Audit of Cybersecurity LLM Benchmarks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08765 - No\=esis: Deterministic-First Retrieval with Two-Tier Context Hydration for Factuality-Critical Queries on Small Local Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07663 - iBrain: A Unified Foundation Model Reading the Brain from Surface to Spikes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06960 - MEMOBench: A Process Level Memory Benchmark for Robotic Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07047 - Interface-Aware KV Cache Quantization for Dense On-Chip NVM in Long-Context LLM Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05764 - A solution to the Erd\H{o}s Problem #1040 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06050 - ViT3Flow: A Test-Time Training Transformer MeanFlow for Postoperative Radiograph Synthesis in Scoliosis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05579 - SequenceO1: End-to-End Ultra-Long (100K) Sequence Modeling in Recommendation with Low-Rank Caching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08443 - Inference-Time Graph Engineering for Multi-Agent LLM Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05774 - A Computational Implementation of a Goal-Directed Theory of Affect Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06654 - X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASR Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08672 - When and Why LLM Causal Priors Help: Closed-Loop Prior Selection for Amortized Causal Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06941 - Agentic Algorithm Engineering: Improving Shared-Memory Exact Minimum Cuts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07204 - When Can One Obtain Certificates of Optimality Using Positivstellensaetze? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08736 - TTGBench: Benchmarking Topological Evolution and Semantic Drift in Text-attributed Temporal Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08226 - Sparks of In Silico Cognitive Science: Theories from Simulated Data Can Generalize to Humans Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08003 - Compiling VGDL into Causal Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05459 - Key Path Identification for Resolving Knowledge Conflicts via SAE-based Steering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08173 - Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliability in Medical Imaging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07803 - SkillAlign: Aligning Skill Interfaces for LLM-based Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07255 - DAREBench: Deployment-Aware and Reliable Evaluation of Models as Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06059 - World Models Under Asynchronous Sensor Observations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07299 - TDDN: Text-aligned Diffused DINO Network for Puzzle Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07937 - Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07099 - Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06731 - FastE: Readout-Triggered Token Compression for LLM Embedding Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08407 - Quantile-Led Feature Extraction for Multi-Horizon Predictive Maintenance in Industrial Manufacturing Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07533 - Multiple Myeloma Lesion Segmentation on Whole-Body Diffusion-Weighted Imaging via Efficient Anatomical Anticipation and Multimodal Confirmation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06165 - PRIMUS: Identity, Governance, and Verification for Multi-Agent Federations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07910 - Improving Proficiency and Efficiency of Android GUI Agents via Self-Generating Tool Actions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06792 - TFTrack: A Template-Free Framework for Efficient 3D Point Cloud Tracking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07738 - CriticGen: Generation-Aware Evaluation as Actionable Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05439 - Intent Drift at SME Scale: Deployment Practice, Not Model Capability, Determines Agentic Compliance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05975 - When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07462 - AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08572 - RedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context Serving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07008 - The Surprising Effectiveness of Approximate Value Iteration in Self-Play Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09094 - Beyond "AI Helps Humans": Decision-Targeted Evaluation Design for Human-Agent Teams in the Agentic Era Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05527 - A Multi-Modal Perception Pipeline for Object Detection and Tracking in Autonomous Racing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08338 - AttnCompress: Dynamic Attention-Guided Trajectory Compression for Software Engineering Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08318 - AuthBench: A Large-Scale Multilingual Benchmark for Authorship Representation across Genres and Lengths Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06771 - AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05899 - A radiographic world model for clinical reasoning and evidence generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07719 - Solving versus Verifying: Catching Contradictions in Tax Reasoning Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05928 - Companion-style QA Assistance in Ego-Vision Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.06721 - PGP-Clinical-TimeKAN: Prior-Guided Joint Probabilistic Forecasting of Clinical Trajectories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05488 - Convergence issues in Relational Concept Analysis based on AOC-posets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00054 - Neptune: An AI model for Global Ocean Subseasonal Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08606 - Evidence-Grounded Retrieval for Investigation Hunt Lead Generation from CTI Reports Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08790 - Frequency Estimation Based on SNR-adaptive Frequency Estimator Under Wide SNR Range Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07034 - Artificial Intelligence-Assisted Digital Inventory of Cultural Heritage & Traditional Knowledge: Case for Indonesian Open Digital Library of Culture Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08105 - CS-CLIP: Compositional Scene Graph-guided CLIP for Robust Compositional Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08242 - The Normalization of Deviance in AI Development Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05749 - Unsound Search with Policy and Value Networks in Legends of Code and Magic Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06816 - Beyond Right and Wrong: Evaluating Second-order Social Reasoning in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05437 - Decentralized Safe Multi-Agent Reinforcement Learning via Predictive Shielding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07618 - Diamond Agent: Agentic Control of Federated HPC Resources as a Service Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06181 - A Unified Policy Architecture (UPA): The Governance Kernel for Enterprise AI Operating Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06543 - Deep Learning for Biopsy-Free Subtyping of Basal Cell Carcinoma from Dermatoscopic Images Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07180 - Novel Methods for Catheter and Guidewire Segmentation in X-ray Fluoroscopy under a Federated Learning Setting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06876 - CWF: A Collaborative Writing Framework for Personalized and Reliable Popular Science Writing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06126 - Agentic BAIM-LLM Evaluation (ABLE): Benchmarking LLM Use of Protein Design Tools Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.05818 - CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07434 - Neural Symbollic Regression Using Deep Learning and Sparse Modelling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01102 - Automated Design of Inventory Policy with Large Language Models: An Exploratory Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08071 - MV-STRIDE: Enabling MLLMs to Master Multi-View Spatial Reasoning via Hierarchical Capability Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07258 - SRD-GUARD: A Defense Framework of LLMs via Semantic Rewriting and Joint Multi-Model Scoring for Latent Intent Exposure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06540 - Bigger Text Encoders Can Hurt CLIP Zero-Shot Performance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05730 - Scratchy: Visual-Scratchpad Multimodal Reasoning for Cryptographic Proof Generation in EasyCrypt Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06226 - Human-agent discovery of reconfigurable in-plane ferroelectric superdomain control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06887 - PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08965 - Versioned Transitive Dependency-Closure Binding and Operation-Time Effect Governance for Agent Skills: ClosureBound Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05920 - Inference-Time Nash Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08082 - Open Tabular Insight Extraction: Where Do We Stand, and Where Should We Go? Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.07629 - Flawed but Memorable: Student Critical Reception of Interest-Personalized GenAI Analogies in Computing Education Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06095 - Learning Counterfactual World Models for Embodied Reasoning under Partial Observability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05834 - Do Dynamic Routers Need Memory? HeRo: History-Aware Routing for Efficient LLM Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08189 - Does Deeper Reasoning Compromise Alignment? Revealing and Mitigating of Alignment Collapse in Large Reasoning Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08186 - Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08418 - Dual-Latent Memory Routing for Vision-Language Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05539 - An emancipatory vision for designing (generative) AI for learner flourishing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07715 - DPSF-Net: A Dual-Prior Spatial-Frequency Network for Real-World Remote Sensing Image Dehazing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06962 - One MLLM, One Call: Efficient Zero-Shot Vision-and-Language Navigation via Spatial-Aware Waypoints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06476 - TC-Next: Zero-Shot Multimodal Cyclone Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02085 - Silent Revision: Measuring Undisclosed Change in the Safety Frameworks of Frontier AI Developers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08789 - Eliciting Self-Verification in Multimodal Reasoning Agents with Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08025 - TriCCOT: Tri-part Convolutional Conformal Transformer for Onboard Space Object Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08659 - A Layered Analysis of Disagreement And Answer Quality in Multi-Agent LLM Debate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08016 - A visual large language foundational model for medical image recognition using clinician-oriented social media Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06914 - What LLM Trading Agents Actually Do in Production: A Six-Month, Population-Scale Record from Two Fleets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05663 - ExecCritic: Learn to Test, Test to Improve for Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09133 - Multimodal Resource-Exhaustion Attacks on Vision-Language Models via Joint Pixel-Prompt Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05889 - Query-Aware Token Budgeting for Efficient Late-Interaction Visual Document Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07262 - Concord: A Video Relational Algebra for Cross-Modal Query Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05756 - Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08966 - Beyond Cross-Lingual Transfer: Benchmarking Propagation Boundaries in Multilingual LLM Unlearning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05976 - Staying on the Attack Path: Structured State for Long-Horizon Automated Penetration Testing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07344 - LLMs for Social Network Modeling: From Network Generation to Dynamic Processes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08049 - Situation Awareness for Intelligent Data Distribution in Connected Vehicles Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05521 - The convergent laboratory: when AI reasoning, autonomous experiments, high performance and quantum computing reshape chemistry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05643 - Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07379 - SAP: State-Guided Data Synthesis with Argument Provenance for Multi-Turn Tool Use Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06124 - Evidence-Aligned Local Composition of Discrete Experts for Sequence Restoration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05801 - Recompilation Is Not Enough: Test-Guided Decompiled-C Repair Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07201 - Mathematical Programming in Machine Learning and Artificial Intelligence: A Unified Taxonomy of Models and Applications Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.07254 - ACEA: An Adversarial Co-Evolution Arena for Head-to-Head Red-Team and Blue-Team LLM Testing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08256 - SIDE: Sensor Impersonation Detection at the Edge via Sequence Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06271 - From Concentration to Differentiation and Back: Routing Effective Rank in MoE Reasoning Cohorts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06403 - Bait-and-Recover: Poisoning Internal Refusal Signals to Defend LLMs against White-Box Editing Jailbreaks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05794 - AURA-Eval: Evaluation Framework for Acting Under Risk Awareness in LLM Agent Trajectories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06783 - Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08267 - RAGMark: A Comprehensive Framework for Benchmarking Retrieval-Augmented Generation Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05760 - Quantifying the Engagement Trap: Impact of Short-form Video Recommender Systems on Users with ADHD Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07795 - Dual-Layer Semantic-Spatial Belief Mapping for Aerial Object Goal Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08164 - BIFTA: Brain-Inspired Few-Shot Tactile Adaptation for Unknown Sensors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08673 - Geometry-Aware Test-Time Learning for Quantitative Spatial Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06004 - Re-calibrated Contrastive Loss for Transformation-Aware Prompt Conditioning in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06967 - PhysMAS: Physics-Grounded Multi-Agent Synthesis of Compositional 4D Gaussians Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07174 - The Failure Happens Before the Drift: The Social Dynamics of Values in LLM Agent Societies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05514 - SCAFFOLD: Self-Improving Web Agents via Recursive Parametric Skill Abstraction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05511 - AI for AI: Optimizing Additional Infrastructure Build-out to Power Artificial Intelligence Data Centers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08166 - SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08149 - Flow3D-OPD: Multi-Teacher On-Policy Distillation for 3D Geometry Generation with Flow-Matching Diffusion Transformer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07137 - Recovering topological information of light by topological learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06542 - SCRIPTIOC-BENCH: A Benchmark for Recognizing Actionable Threat Intelligence from Script-Based Malware using LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06149 - WSPolypNet: Weakly Supervised Polyp Localization in Colonoscopy Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08182 - Human mutation field reveals an equilibrium-like structure with irreversible circulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07500 - A Data-Driven Framework for Identifying and Prioritizing RPA Opportunities in Healthcare Processes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09137 - Reading Decoder Trajectories: Training-Free Counterfactual Query-Trajectory Reliability for Small-Object Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06581 - Qiushi Engine on AstaBench E2E-Bench-Hard Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08196 - AVSplat: Dense-View Feed-Forward 3D Gaussian Splatting with Assist-View Preconditioning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05925 - zScore-N: A Neural Network for On-Chain Wallet Reputation Scoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08247 - Unraveling the Real Working Mechanism and Inherent Flaws of GAE: A Method for Interpreting Transformer Processes from an Economic Perspective Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07213 - Closed-Loop Evaluation of Bird's-Eye-View Maps from Cross-View Transformers as Inputs to Behavior-Cloning Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05783 - WolfSociety: Understanding Collective Risk from Harmful-Agent Scaling in Financial Agent Societies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05591 - AgentIdeaBench: Benchmarking Scientific Ideation in the Agent Era Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07611 - Mini-Batch Risk-Averse Deep Q-Learning: A Robot Navigation Case Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07998 - AV-SafetyBench: A Safety Benchmark for Text-to-Audio-Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06991 - From Simulated Citizens to Simulated Deliberation: Challenges in Representation and Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07573 - Your Agent Says Yes: Interpreting Adversarial Market Behavior Beyond Individual Transactions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07675 - We're Cooked! - Probing LLM Political Alignment Via Conflict-Framed Recipe Translation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07568 - When Does Memory Help? A Cost-Aware Evaluation of Long-Term Memory in Tool-Using LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05441 - When Agent Governance Helps Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05531 - Exposing Weaknesses in Emotion Recognition in Conversations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05806 - A Translational Note on AI Safety Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06573 - It's All in the Way You Say It: The Role of Information Representation in LLM-Based Glycemic-Event Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08772 - SAFIRE: Safety-Critical Benchmark for Fine-grained Fire and Smoke Understanding in Multimodal LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07823 - MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive Merging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08273 - FACT: A Forensic Agent with Compiled Tool-Use Trajectories for AI-Generated Image Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05876 - SCIRIGOR:Evaluating Open-Ended Scientific Analysis Beyond Final Scores Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06192 - Beyond Final Decisions: A Process-Centric Benchmark for Transparent AI-Assisted Peer Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05947 - Emergent Goal-Directed Attention in Large Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05517 - Explaining AI Agents Through Execution Traces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06063 - RAPID: Reliability-Aware Pair Importance Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05481 - Causal Attribution for Agentic Decisions: Estimators, Coupling, and a Traceability Specification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06445 - 3DWay: Generalizing Robot Manipulation via 3D Consistent Waypoints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08224 - A Trustworthy Watermarking Framework for LLM-Generated Food Safety Content Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06708 - The Role of Gradient Modification in Heavy-Tailed Nonconvex Stochastic Min-Max Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06064 - SkillAdam: Stable and Efficient Skill Evolution for Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08944 - Topology Obstructs Pure Foundation Neural Quantum States Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07591 - Harnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07670 - DART: A DAG-Based Reputation and Incentive Framework via Blockchain-Enabled Governance for Trustworthy LLM Multi-Agent Collaboration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05529 - AutoFyn Technical Report: Non-Parametric Expert Iteration for Long-Horizon Agents Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.05446 - The Internal Anatomy of Strategic Choice in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07478 - What Eviction Destroys: A Restore-Counterfactual Audit of Forgetting in Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08279 - The Profit Alignment Problem: How Profit Mandates Induce Alignment Failures in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07731 - FinCUABuild: Can Agents Build Reliable Benchmarks for Dynamic Financial Computer Use? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07603 - Adaptive Cost-Sensitive Machine Learning for Autonomous Robot Navigation Failure Prediction: When Not All Errors Are Equal Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05593 - SciLitBench: Benchmark and Design Principles for LLM-Powered Systematic Literature Reviews Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05505 - Collision Snapshot Guided Time-Reversed Safety-Critical Scenario Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06433 - STAR-Pro: Stage-Wise Token Adaptive Reduction with Progressive Refinement for Efficient Large Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05916 - Microcanonical Hamiltonian Monte Carlo and the Helmholtz Theorem Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07620 - OntoKG-EQ: A provenance-grounded, competency-question-governed knowledge graph for auditable analyst querying Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08869 - Segment Any Motion with Radar: Robust Multimodal Moving-Object Segmentation and Tracking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08346 - AstroSpecLM: A Spectrum-Language Model for Evidence-Grounded Astronomical Spectral Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07102 - MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09115 - Exploring Bottom-Up Clustering for Creating Semantic IDs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08310 - Closing the Consistency Gap: Self-Evolving Agents That Learn to Stay on Course Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.08832 - Monte Carlo-Based Ex-Ante Assessment of the Green Benefits of an AI-Driven Smart Agriculture Platform in Hainan Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06737 - Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Method Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08402 - The Unreliable Progress Bar: Can LLM Agents Reliably Report Task Progress Throughout Execution? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08589 - Solution for UCF UrbanTwin LUMPI Track: Sim-to-Real Urban LiDAR 3D Object Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07590 - TamilEOT: A Dataset and Model for Semantic End-of-Turn Detection in Tamil Telephone Speech Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05631 - Subject-Relative Micro-Motion and Sleep Dynamics for Near-Infrared Video Sleep Staging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05550 - XYBench: Can LLMs Respond Pragmatically to Queries with Misconceptions? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06842 - WAPP: Safe Learning of Positive Security WAF Policies from Live Traffic Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06840 - Noise Adaptive Streaming Audio-Visual Speech Token Enhancement for Robust Full-Duplex Spoken Dialogue Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08390 - Customer Relationship Intelligence: Integrating CRM and MDM for Enhanced Customer Engagement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06189 - When Intelligence Becomes Agency: A Theory of Governed, Proactive Agency for Symbiotic AI Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07741 - Three Types of Negation of Triple and its Elements and an Extension of Triple Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08271 - FPicker: Topology-Guided Evolution for Filament Tracing in Low-SNR Microscopy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08305 - CLAMP: Constrained Decoding for Vision-Language Embodied Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08602 - Zero-Shot Sim-to-Real Contact-Rich Assembly via Proprioception-Anchored Cross-Modal Pretraining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07534 - Building Trustworthy Graph-Agentic RAG for Social Good: Architectures, Failure Propagation, and Assurance by Construction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06391 - Large-Scale User Behavior Analysis in Multimodal AI-Assisted Manual Task Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07594 - ObGynLongBench: Revealing the Evidence-to-EHR Gap in Longitudinal EHR Decision-Making Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07601 - Image-Scale Robustness and Visual Recognition Performance: A Cross-Architecture Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06051 - BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07362 - Diffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generation for Flutter/Dart Code Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05779 - Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07139 - Phase Structure in Rotary Attention: A Spectral Framework for Semantic Continuity and Execution-Boundary Governance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.25507 - CityPlanner: A Sandbox Agent for Executable Urban Planning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09578 - Vague2Detect: Handling Ambiguous Prompts in Knowledge-Based Open-World Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09949 - $S^3$-Bench: Evaluating Speech Interaction Models as Scientific Voice Assistants Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09852 - TEFM: Token-Efficient Faithful Modeling for Structured Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09552 - Contrastive Projection: Reading Transformer Internals by Differencing Logit Lenses Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09902 - Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09233 - CARRE: Counterfactual Action Retrieval and Reason Evaluation for Explainable Churn Prescription Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09766 - Preserving Long-Tailed Expert Information in Mixture-of-Experts Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.23036 - From Rubrics to Reliable Scores: Evidence-Grounded Text Evaluation with LLM Judges Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.08654 - EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13841 - Benchmarking Hybrid Deep Research Across Database Querying and Web Search Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09410 - Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18216 - Osprey: Target-agnostic Pre-training Makes Stronger Drafters in Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09338 - StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09264 - Scaling phoneme-based TTS augmentation for ASR: A unified pipeline and controlled study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26697 - Who Argues What? Joint Argument-Entity Detection and Classification in Political Debates Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10192 - Qwen-Audio-3.0-ASR Technical Report Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07549 - Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16023 - Elsewise: Authoring Open-ended Interactive Narrative with Possibility Space Visualization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15295 - Less is MoE: Trimming Experts in Domain-Specialist Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05538 - Cultural Binding Heads in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28543 - Reproducing Omitted Temporal Expressions in Japanese News for Retrieval-Augmented Applications Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09569 - Strangers to Themselves: What Language Models Say About Themselves Is Generic Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09899 - SalamandraTA at WMT 2026 Terminology Shared Task: Hard Examples Are Better Teachers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09999 - Multi-Level Narrative Evaluation Outperforms Lexical Features for Mental Health Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.27846 - Deep and shallow biases in language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09901 - Stable Answers, Unfinished Reasoning: Why Self-Consensus Is Not a Safe Early-Exit Signal Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09989 - NOPE-HYPE: A Structured Simulation Workflow for Robust Speech-to-Text Across Diverse Acoustic Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10058 - Less Is Personal: Learning Minimal Sufficient User Profiles for Personalized Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08180 - RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10305 - 'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24191 - The Mutations of Machine Speech Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.09496 - Light or Full Verb? A Minimal-Pair Dataset for Probing Phraseological Competence in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05087 - LogiScope-VQA: Benchmarking Vision-Language Models for Logistics Hazard Identification in Industrial Scenarios Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09790 - "What Are You Really Trying to Do?": Co-Creating Life Goals from Everyday Computer Use Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00497 - Do LLMs Make More Mistakes If They Do Not Believe the Input Data? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09363 - ProbPlug: A Plugin Uncertainty Network for Reliable Confidence in LLM Binary Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10122 - Looped GPT-BERT: Trading Parameters for Computation in Small Language Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09691 - AI translation of literary texts is "fine", but readers still prefer human translations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26040 - Expert-Level Crisis Detection in Mental Health Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10380 - Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10052 - Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04298 - A Patient Simulation Framework for Risk Assessment of Conversational Healthcare AI: Evaluation of an Antidepressant Decision Aid Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11391 - SocialRL: Refining LLMs' Social Intelligence through Multi-turn Reinforcement Learning and Reward Design Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09764 - Am I More Pointwise or Pairwise? Revealing Position Bias in Rubric-Based LLM-as-a-Judge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02219 - UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09815 - ActTraitBench: Quantifying the Knowledge-Decision Gap in Large Language Models via Human-Grounded Behavioral Validation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29791 - VestigeKV: The NoPE-MLA KV Cache Carries Its Own Sparse-Attention Signal in a Vestigial Branch Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03949 - Do speech foundation models really learn words? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10434 - What Does MMLU Actually Measure? A Psychometric Audit of Difficulty Structure in Aggregate Benchmark Scores Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09372 - 5-Dialects-BN: Unmasking the Impact of Transliteration on Bangla Dialectal LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09964 - SymbolicLight V2: Hybrid Neuromorphic Architecture and Sparse Execution for Low-Energy Language Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09772 - IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10494 - LLM-Generated or Human-Written? Comparing Review and Non-Review Papers on ArXiv Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17036 - Towards Automatic Evolution Tree Generation from Citation Graphs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09561 - Revisiting the Shape Convention of Transformer Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06471 - KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10266 - SEA-SpeechBench: A Large-Scale Multitask Benchmark for Speech Understanding Across Southeast Asia Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09672 - From Representation to Enactment: The ABC Framework of the Translating Mind Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.16811 - Tracing Computation Density in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27033 - Politics of Feelings: Emotional Expression and Legislative Effectiveness in the U.S. Congress Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10198 - Two-Token Features and Small-Large Ensembles for VLM Hallucination Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10244 - A Resource for Enthymeme Detection in Controversial Political Discourse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12186 - See Better, Foresee Better, Act Wiser: Physically Grounded Proactive Modeling and Decision Making Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03371 - Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15129 - Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10142 - Where is the Mind? Persona Vectors and LLM Individuation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17031 - Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09241 - MedDeID enables locally governed clinical-text de-identification from real or synthetic training data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10049 - BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09554 - PELM: Power Efficient On-Device LLM Inference with Speculative Decoding and Dynamic Voltage Frequency Scaling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09662 - Multi-Functional Embedding Models for Funder Name Disambiguation in Scientific Publication Records Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09984 - Improving Cross-Lingual Token Representations by Adding a Pinch of SALT Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09953 - BTBR: A Bayesian-Theory-Driven Probabilistic-Fuzzy Framework for Implicit Bias Removal in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2408.10608 - If It's Not Buggy, Don't Fix It: On the Dynamics of Iterative Bug-fixing with LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10123 - Towards Stress-Aware Sentence-Level Filipino G2P With Weakly-Supervised ByT5 Fine-Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09974 - SEA-LION-Embedding: Open and Reproducible Text Embeddings for Southeast Asia Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03027 - DiSCo: A Distribution-First Steering and Cultural Prior Evaluation Framework for Measuring Cultural Preference Bias in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10253 - TokEval: A Tokenizer Evaluation Suite Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18062 - ROAM: Robust Organization of Atomic Memories for Agents through Semantic Relations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09778 - VLX-VR: An Agentic-Aware Video Reasoning Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09985 - Dynamics of meaning: Towards the Evaluation of Diachronic Semantic Change in Sinhala Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08609 - Can Artificial Intelligence Support Healthcare and Mental Health Through Early Cyberbullying Detection ? The Impact of Emotion-Aware AI on Proactive Online Safety Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09735 - MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10016 - Beyond Top Words: MonoTM for Topic Modeling with Interpretable Monosemantic Features Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09575 - When Does Defendant Statement Matter? A Study of Bias and Persuasion in LLM-Simulated Jurors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09887 - StreamAlign: Streaming Text-Aligned Speech Tokenization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09719 - Through the Looking Glass: Directly Reading and Writing Transformers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10210 - HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09835 - AgenticGen: Reward-Guided Agentic Video Generation for Advertising Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09187 - From Fixed Keys to Readable Schemas: Small Language Models for Vehicle Agent Function Calls Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09476 - Edu-QuRating: Multi-Dimensional Educational Data Curation with Distilled Pairwise Judgements Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09425 - AtlasNLP: A Country-Aware Atlas of Dataset Representation in NLP Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30107 - SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21384 - YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10153 - RAP: Research Attention Prediction Reveals Target-Conditioned Evidence Acquisition Biases Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10092 - Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.10701 - An Efficient and Effective Agentic Group Shilling Attack on Recommender Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09551 - Who Are They to Each Other? Multi-Agent Reasoning for Speaker Relationship Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09628 - False positive bias in AI-powered speech-based cognitive screening for multilingual English speakers in the UK Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13047 - Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10410 - Fine PT-PT Web: A High-Quality 41 Billion Tokens Data Collection of the European Portuguese Web Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07699 - Auditable Emergency Triage for Maternal and Newborn Care in India Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09356 - Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10355 - From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10335 - MultiSynt/MT: Trillion-Token Multi-Parallel Pre-Training Data Translated Across 36 Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.00890 - IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10539 - Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28707 - $\Phi$-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10226 - MUCnoHARM@GermEval Shared Task 2026: Retrieval-based In-Context Learning for Defamatory Offences, and Where It Falls Short Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09791 - Leveraging Fine-grained Error Correction in Korean Speech Recognition for Consultation Services Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09889 - TreeThink: A Modular Tree Search Library for Mathematical Reasoning with LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11258 - Reading a Legal Question Word by Word: Embedding Trajectories of 2,144 Vietnamese Legal Headlines Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08372 - When Do Large Language Models Exhibit Unsolicited Deception? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.00285 - When Auditors Fabricate: Batch-Size Degradation and Confident Hallucination in LLM Detection of Planted Document Contamination Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09696 - Scaling E-Commerce Attribute Extraction with Parallel Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09716 - FrontierChallenge: Evaluating Scientific Workflow Completion Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24979 - MADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.05124 - BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03504 - Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09768 - MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09206 - X-CoSD: Communication-Efficient Cross-Vocabulary Collaborative Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09166 - Are LLMs Positionally Consistent Ordinal Classifiers? A Systematic Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08869 - Deterministic Prompting for Speaker-Stable Low-Resource Greek TTS Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10022 - Data-Centric Post-Training for Financial Reasoning: Mining, Distillation, and Verifiable Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10113 - Rosetta at AlexandriaX-2026: LoRA-Adapted NileChat for Context-Aware Dialectal Arabic Dialogue Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10395 - X2-NativeCursor: Native-Token Text Progress Tracking for Incremental-Text Streaming Codec TTS Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09677 - Leveraging Speech Acts for Low-Data and Cross-Domain Conversation Derailment Forecasting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25359 - SWORD: Wikidata-based Distortions Reveal Hidden Cross-Lingual Inconsistencies in LLM Factual Error Rejection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09349 - Copying explains the collective behavior of AI agents in the wild Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09150 - Which Medical Questions Deserve Rationales? Perturbation-Sensitive Selection for Robust QA Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09684 - EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.27695 - ConvMem: Convolutional Memory for Long-Context Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10441 - Two tests of phase-structure features for transition prediction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00335 - On-Policy Distillation for Vision-Language Model Adaptation, an Effective Paradigm on Low-Quality Multimodal Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10321 - Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16620 - OntologyAligner: Ontology-Aligned Retrieval and Hierarchy-Guided Large Language Model Reranking for Biomedical Ontology Normalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10055 - The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10296 - In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09243 - Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling Perspective Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.15047 - How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09793 - Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10445 - From Scores to Evidence: Auditable Decisions Can Improve Speech Deepfake Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08899 - Retrofitting Code Using LLMs to Support Exceptional Behavior Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10397 - LatentDx: Latent Multi-Agent Communication for Cross-Hospital Rare-Disease Diagnosis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13945 - Better Together: Complementary Query Rewriting Under a Strong RAG Baseline Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.05637 - Purchase Advice and Observable Buyer Responses in Real AI Conversations Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.09878 - Glyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data Catalogs Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.10430 - Should I Be Polite to My LLM Relevance Judge? Tone as a Severity Operating-Point Shift Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.09703 - LiteRAG: Cost-Efficient Graph-Based Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.10239 - From Retrieval to Weights: Parametric Individualization of Small Language Models with Individual Text Corpora Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.10155 - Query Brand Entity Linking in E-Commerce Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2502.01555 - LoopMemGR: From Behavior Logs to Evolving Memory for Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2607.27647 - DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.11889 - On the Capacity of Distinguishable Synthetic Identity Generation under Face Verification Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2604.10641 - Extracting Semantics from Cattle Reporting Categories for Data Interoperability and Findability Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.09381 - Guaranteeing Faithful Evidence Extraction in Speculative Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.10046 - GANDR: Claim Auditing for Verifiable Legal Answer Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.10293 - High-probability guarantees for linear accessibility in feature superposition Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.09556 - When Does Low-Bit Quantization Preserve the Decisions of Vector Search? Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.09854 - The Answer Path and the Grounding Instruction in LLM Question Answering over Knowledge Graphs Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.10237 - Tight Lower Bounds for State Tomography with Limited Entanglement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05718 - AlphaRJM: Reward-Jump Memory for Stochastic Return-Guided Alpha Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08581 - A Multi-Source Ensemble Approach to Candidate Generation for Alternative Vacation Rental Property Recommendations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05748 - Capsule Lens: Locating and Tracking Concept Geometry in Model Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05575 - Nearly Tight Rademacher Bounds for Sparsely Activated Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09130 - Cadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06008 - Hierarchical Fourier Approximation for Variational Quantum Distribution Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06307 - Beyond Arbitrary Geometry: Topology Generalization In neural PDE Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05860 - AstraMoE-SR: Trajectory-Guided Diffusion for Blind Satellite Jitter Deblurring and Super-Resolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07012 - Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08084 - Forecasting the Winner of a Live Tennis Match Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07617 - Adaptive Nonlinear Vector Autoregression: Robust Forecasting for Noisy Chaotic Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.08738 - Representation learning of human cortical folding to reveal long lasting neurodevelopmental signatures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05438 - Structured Extrema Errors in Classical Surrogates for Viscous Burgers: A Physics-Consistent Interpretation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07952 - FedSubMuon: Communication-Efficient Federated LLM Fine-Tuning via Structured Subspace Muon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06073 - Multi-granularity Adaptive Hypergraph Representation Learning via Granular-ball Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05574 - Projected Neural Differential Equations for Learning Constrained Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.23667 - Aha-Flow Distillation: Flow Markers Matter in LLM Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07036 - SolarBench: A global solar energy nowcasting benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06187 - Non-Adaptive 1-Bit Mean Estimation: Minimax Rates and the Sample-Interval Tradeoff Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08564 - Transformers as In-Context Samplers: From Closed-Form Diffusion to Estimation-Free Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08981 - A dictionary learning framework for graphs via filters and optimal transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05919 - VERPO: Verified Evidence Regularized Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06100 - Riemannian Optimization for Multi-Player Quantum Games on Product Unitary Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07397 - A Theoretical Framework for Masked Pretraining (MPT) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06460 - Programmable Cellular Automata Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06102 - Instance-wise Linearization of Neural Network for Model Interpretation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2310.16295 - Omni Interaction Agent Technical Report Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08977 - Granular-Ball Quantum Clustering for Resource-Efficient and Robust Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06016 - TabBench-Bio: A Living Benchmark for Machine Learning on High-Dimensional Biomedical Tables Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07441 - PhysSAE: Mechanistic Interpretability with Sparse Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07061 - Multi-Task Learning for Sparsely-Labeled Time Series: A Case Study on Cold-Hardiness Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09062 - Recovering linear images of sparse signals from indirect observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06182 - MLIP Detective: Active Failure Mode Discovery Beyond Benchmark Scores for Machine-Learning Interatomic Potentials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08399 - ZetaDial: dialing net charge of protein binders at inference time for therapeutic developability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05451 - SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09113 - Learning Length-Extrapolatable Recurrent Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09157 - Do Quantum AIs Dream in Paths? Path-Integral Slow Thinking through Grover Interference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05842 - Resolving sources of uncertainty in AI weather forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.14218 - Topological Fraud Detection in Latent Transaction Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08445 - Bi-HYCO: Bi-Objective Cooperative Learning for PDE Parameter Identification under Fragmented Observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06511 - You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07808 - Exact Record Omission in Delta Attention: A Transport Criterion, Its Cost, and a Replay Certificate Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06872 - Srijika: OpenType-Layout-Reusing Font Restyling for Nine Indic Scripts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05661 - TSMini: A Simple Yet Highly Effective Trajectory Similarity Learning Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.00285 - Accuracy is Not Enough: A Divergence-Based Approach to Evaluate Fidelity Loss in Quantized LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07664 - Deep Barycentric Regression for Optimal Transport Map Estimation and its Statistical Optimality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06598 - When Does Scale-Invariant Optimization Become Unstable? An Exact Schedule Law with Weight Decay Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09116 - Separating Capability from Confidence: Grounded Dual-State Calibration for GRPO-Trained Medical Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06419 - Decomposing LLM-Judge Uncertainty to Target Expert Labels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06444 - Flexible Spectral-Normalized Neural Gaussian Process for Dynamic Aperture Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08620 - High-dimensional Linear Bandits with Knapsacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2311.01327 - Learning Adaptive SED for heterogeneous load balancing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06881 - Understanding Uncertainty Sampling via Equivalent Loss Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2307.02719 - FALCON-S: Fixed-wing ground-effect Aerodynamics Simulator and Flight Control Learning Suite Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06046 - A Nuclear-Norm Lower Bound for Dithered Scalar Quantization of Matrix Products Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05641 - A Gradient-based yet Spike-Timing-Dependent Solution to the Feedback Learning Problem in Neural Microcircuits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08070 - Characterizing Privacy Risks of Quantum Machine Learning with Emergent Quantum-Native Access Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05702 - Multi-Level-Set-Based Physics-Driven Neural Network to Solve 3-D Inverse Scattering Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08594 - Discovering Translation-Worthy Languages with E-Values Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06593 - Large Classification-Risk-Optional Label Acquisition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06873 - Learning Latent Graph Geometry via Fixed-Point Schr\"odinger-Type Activation: A Theoretical Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.20088 - Observability conditions for neural state-space models with eigenvalues and their roots of unity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.15758 - Trust-But-Verify: Poisoning-Resilient Locally Private Graph Learning Protocols Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07063 - Condition aware learning enables robust prediction of oligonucleotide melting behavior across diverse chemistries and assay conditions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05454 - PAC-Private Autoregressive Generation: Calibrating Noise to Ensemble Disagreement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05676 - Smoothed Picard Hamiltonian Monte Carlo Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06906 - Improving Multivariate Time Series Classification with Class-Wise Training and Model Aggregation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07493 - MetaKV: Adaptive KV Cache Compression for Constrained LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07966 - Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09030 - Deep Learning Approach to Bearing and Induction Motor Fault Diagnosis via Data Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.11032 - BinauralVAE: Spatial Audio Reconstruction For World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06837 - MARBO: Relational Belief Grounding for LLM Agents in Social Deduction Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06563 - KBBQ: A Predictive Noise Law and the Limits of Spectrum Flattening in FP4 Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08135 - Dense Structural Compression of Transformers via Gauge-Correct Channel Removal Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07264 - A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07821 - Minimizing the Effect of Sleep Deprivation in the Forward-Forward Algorithm Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06042 - Likelihood-Based Unsupervised Anomaly Detection in CMS Dijet Events Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06686 - Open-Set Domain Adaptation Under Background Distribution Shift: Challenges and A Provably Efficient Solution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.01152 - Counter-Swarm Doctrine: Containing Coordinated Agent Intrusions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06140 - One Shared LoRA Weight for MRI Reconstruction across Acceleration Factors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06338 - Stochastic Nonconvex Bilevel Optimization: Improved Rates Without Rare-Visit Assumption Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06580 - Protocol effects on feature-based hardware-Trojan detection across Trust-Hub families Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07199 - A First-Order Learning Algorithm for Online Resource Allocation with Constant Regret Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05895 - Temporal State Transport in Video Generation: Diagnosing and Correcting Spectral Imbalance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08505 - MamMA: A Mamba-Based Pedestrian Trajectory Prediction Algorithm Considering Occupancy Map and Pedestrian Awareness States Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08041 - Proper Dataset Valuation by Pointwise Mutual Information Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.18253 - GradeTrap: Authority Cues in Images Shift VLM Judgments Despite Explicit Instructions to Ignore Them Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06058 - AI and TCAD for Inverse Design and Defect Discovery: From Simple Machine Learning to LLM Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07046 - Heat Kernel Textures: the Geodesic Gaussians That Do Not Splat Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07557 - Decision-Aware Suffix Prediction and Reasoning of Business Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06169 - Dynamic-Programming-Guided Hierarchical BPE and Empirical Analysis of Vocabulary Pruning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06898 - RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05738 - A Closed-Form Estimator and Diagnostic Battery for Anchor-Judge Error Correlation, Under a Single-Common-Factor Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08826 - Temporal Kolmogorov-Arnold Networks (T-KAN) for High-Frequency Limit Order Book Forecasting: Efficiency, Interpretability, and Alpha Decay Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.02310 - Policy Gradients for Cumulative Prospect Theory in Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.02605 - Adaptively Incorporating Directional Hints into Zeroth-Order Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08277 - Efficient Learning and Symmetry Discovery under Exact Invariances Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07031 - Hardware Trojan Threats to Multi-Chiplet Photonic Neural Network Accelerators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06796 - A Measurement Study of LLM Inference Trade-offs Across Edge Continuum Hardware Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08307 - When Do Options Help? Policy Necrosis and Redundant Coverage in Option-Critic Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05508 - Beliefs and Behavior in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07943 - ZK-Trace: Certified Collusion Tracing with Zero-Knowledge Credentials for Federated GNSS Interference Monitoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08763 - RAFM-SER++: A Lightweight Multimodal Emotion Recognition Framework for Real-Time Behavioral Monitoring in Surveillance Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07409 - RAPTOR: Role-Aware Private Training for Mixture-of-Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05770 - Selective Posterior Margin Regularization for Forward-Corrected Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05859 - A Transformer-Based Delta Expression Encoder for Psilocybin Transcriptional Response: Architecture, Representations, and Biological Validation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08165 - Why shared attention vectors fail: a case for outcome-indexed tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08615 - Beyond Retraining-Free MoE Compression: A Cost-Normalized Study of Post-Compression Adjustment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06076 - Latent class analysis by regularized spectral clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2310.18727 - From Narrative to Auditable Forecasts: A Structured Scaffold for Agentic Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05905 - Grounded and Faithful P&ID Reasoning: Constraining Vision-Language Models with Recovered Evidence Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05880 - I Don't Miss You, but I Do: Self-Explanation Faithfulness of Modality Missingness in Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07596 - Constrained Online Learning with Noisy Constraint Values Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06921 - ThinkPrior: Zero-Rollout Difficulty Priors for Cold-Start Prompt Selection in RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09075 - Selective boundary condition reduction via learned error gating Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08461 - Tracking the Moving Frontier: Long-Short Term Advantage Estimator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06671 - Retrieval-augmented Decoding for Improving Truthfulness in Open-ended Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.02184 - The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persists Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06934 - HyCO: A Hybrid Neural Solver for Combinatorial Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07990 - Stochastically Perturbed Weights: Ensembles from Deterministic Machine-Learning Weather Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08412 - Scalability Analysis of Distributed Kolmogorov-Arnold Network Training on High-Performance Computing Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07740 - A budget-dependent crossover between coverage- and response-based training-set selection for machine-learned interatomic potentials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05877 - What the Window Does Not Contain: Auditing Provenance in a Document-Grounded Instability Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06147 - Assessing Covariate-Informed Grid Load Forecasting with a Time-Series Foundation Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06656 - Geodesic-informed Generative Diffusion Model For Topology-preserved Image Video Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08153 - AF-Mamba: Efficient Long-Term Signal Modeling for Early Prediction of Atrial Fibrillation Onset Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06984 - Equivariance Breaks the Learning Rate Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08381 - Miles v0.1: Production-Level Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08368 - Robust Decentralized Personalized Federated Learning via Prediction-Constrained Neighborhood Collaboration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07312 - Train Smarter, Not Harder: Switching Signal-Guided Training in Active Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06806 - Comparison of D-Wave Quantum Annealing and Gibbs Monte Carlo for Sampling from a Probability Distribution of a Restricted Boltzmann Machine Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.10228 - MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06396 - Attributing Cohen's d: Training Data Attribution for Disease-Related Effects in Normative Age Biomarkers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07729 - Temporal Heterogeneous Graph Transformer for Credit Card Fraud Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07100 - Revisiting Thinning Methods for Kernel Learning Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07432 - Structural Entropy-Driven Graph Diffusion Generation for One-Shot Federated Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06499 - Federated Binary Gating with Server-Side Vision-Language Inference for Surveillance Anomaly Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07403 - Reason Through the Latent! Making Latent Visual Reasoning Necessary Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06746 - Connecting Score Matching, Maximum Likelihood, and Expectation-Maximization in Mixed Linear Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05688 - Robust Decentralized Federated Distillation via Multi-Modality Knowledge Collaboration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07230 - Decomposition-Guided Diffusion Language Models for Inertial Confinement Fusion Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07756 - Linear Algebra Foundations of Efficient Attention: A Phase Reversal in Rank Collapse Under SVD Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06341 - Endogenous Exploration in Reinforcement Learning with Intrinsic Curiosity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05650 - OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06490 - All for 1-Bit: Towards Genuine 1-Bit Post-Training Quantization for LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06161 - Proactive Context-Forecasted Safety Constraints for Nonstationary Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08080 - Recovering Weak Signals with Normalizing Flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06382 - A Systematic Analysis of Automatic Differentiation versus Discretization-based Constraints for Physics-Informed PDE Solvers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07437 - PAC-Bayesian Bounds for Learning Partially Observed Stochastic Linear Time-Invariant State-Space Systems with Inputs and Sub-Gaussian Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08740 - TrojanWorld: Backdooring World-Model Agents via Imagination Steering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07051 - DART: Distributional Adversarial Recurrent Training for Algorithm Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05988 - Neither Adversarial Training Nor Purification: Emergent Adversarial Robustness from Oscillatory Predictive Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08683 - Deposon: An Auditable, Conservation-Guaranteed, Game-Theoretically Tested Scattering Layer over LLM Reasoning Paths Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09001 - Automated Chest CT Protocol Selection via Large Language Model Derived Text Embeddings from Imaging Request Text Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07986 - A Theoretical Analysis of Generalization Dynamics in Neural Networks under Gradient Descent with Weight Decay Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07755 - ACE: Adapter Consolidation across Experts for Parameter-Efficient Fine-Tuning of MoE LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06072 - IPM-FM: A Foundation Model with Consensus Feature Selection for Industrial Process Monitoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08375 - Conditioned Initialization for Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07086 - SeaCausal-FL: Federated Fuzzy Causal Learning for Maritime IoT Fault Diagnosis and Counterfactual Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06257 - Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07072 - Polarity-Asymmetric Structural Calibration for Link Sign Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05896 - SingLEM: Single-Channel Large EEG Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.17920 - Content-Based Addressing for Long Context Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07314 - On-the-go Forgetting without Explicit Unlearning via ERASE Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05966 - To Adapt or Not to Adapt? Selective Adaptation for Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08367 - Gaussian Linear Functional Manifold Method for Massive Point Cloud Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05744 - Impact of canny edge detection preprocessing on performance of machine learning models for Parkinson's disease classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07408 - A Sub-4 Approximation for Fair $k$-Means Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07974 - The Art of Hierarchical Competing Patterns: Gaussian Process Optimization of Hyphenation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07638 - SwiftExplorer: Training-free Diffusion Model Alignment with Swift Diversity Exploration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06651 - $\alpha$-Graph: Attention-Infused Normalizing Flow Approach to Tractable Graph Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07961 - Local and Global Stability in Performative Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06467 - HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08306 - CodeTD: Topology of Attention Detects Hallucinations in Code LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07779 - Chimaera: A Mixture-of-Graph-Experts Architecture for Cross-Task and Cross-Dataset Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08709 - Spatial Feature-wise Linear Modulation (SpFiLM) for Contrast Agent-Aware Brain Parcellation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07718 - SynthRCT: Scalable Conditional Deformation Synthesis for Synthetic Repeat CT Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08627 - Model-Adaptive and Risk-Constrained Frequency Hopping Against Predictive Jammers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06514 - Provable Pluralistic Alignment: Multi-Party RLHF under Offline Human Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2403.05006 - REFINE: Trajectory Representation Learning via Closed-Loop Transcription -- Extended Version Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07206 - Representation Learning for Sample-Efficient CATE Estimation by Leveraging Multiple Outcomes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06294 - Structurally Close, Temporally Distant: Measuring Security Exposure in Long-Horizon LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05911 - An Exploratory Study of Frequency-Aware Task Weighting for YOLOv8-Based Unified Driving Perception Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05516 - Rethinking the Evaluation of Efficiency Methods for Multi-Agent Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05933 - PCFlow: Physics-Conditioned Flow Matching for GPR B-Scan Image Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07300 - TD-STGT: A Spatio-Temporal Graph Transformer for Mobile Traffic Demand Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06636 - Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08404 - PCSDiff: Diffusion-Based Bias Correction and Super Resolution Toward Practical Operational Medium-Term Precipitation Forecast Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06942 - SUN: Reaching for Novelty in Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08642 - Scaling Optimal Classification Trees via Adaptive Feature and Sample Reduction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05826 - Not All Variables Agree: Reliability-Aware Variable-Wise Gradient Surgery for Multivariate Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08554 - Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08798 - Nonlinear elliptic homogenization with the parametric Deep Ritz method Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05778 - ModularPhaseNet: Finite-Cyclic Phase Geometry for Computable Semantic Hierarchy, Direction, and Context Consistency in Standard Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06000 - Data Quality Rule Generation with LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06053 - DataFlex-RL: An Evaluation Platform for RLVR Data Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06107 - A Generalization of Amari's Bayesian Duality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09126 - Inferring Urban Mobility Interactions from Aggregated Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07349 - Parser-Free VLM Verification for Federated Weakly Supervised Video Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07455 - Sparse Oblique Rule Boosting for Simpler Additive Rule Ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06426 - NoLoCo: No-all-reduce Low Communication Training Method for Large Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.10911 - ActionSplice: In-Flight Action Editing for Interactive World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08230 - HOPE: Heterophily-Aware Open-Set Node Classification with Pseudo-Extrapolation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08685 - VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08040 - Mind the Approximation: Fisher-Weighted SVD Compression for ViTs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07155 - Adaptive Anisotropic Attention for Axis-Structured Signals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08788 - DrugReason: Dynamic Multi-View Reasoning over Knowledge Graph and Language Evidence for Drug Repurposing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06779 - Damage-Aware Bandit Pruning for Vision and Language Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05448 - Topology-induced Operators Reveal Complementary Graph Representations without Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08152 - Cross-modal learning for SAR target recognition using optical vision foundation models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07753 - Certified Topological Interaction in Neural Representations: Class Disentanglement Is Mostly Pairwise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08561 - A Better Spur Should Start From Each Objective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08211 - CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08244 - Predicting Wind Turbine Power Using Machine Learning and Weather Forecasts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06194 - Disentangling Steering Vectors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07037 - Risk-Conditioned Fine-Tuning of Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08064 - SFO: Learning PDE Operators via Spectral Filtering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17090 - Generalizing HVAC Control With Domain Randomized Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05822 - Explainable Temporal Attention-based Defect Detection For Fillet Joints in Real-Time Gas Metal Arc Welding Based on Multi-modal Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07893 - Behavioral Cloning Outperforms Entropy-Regularized RL: Critic-Driven Failure of Actor-Critic Methods on Adaptive Tumor Treatment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06667 - Inducing Emergent Misalignment from Reward Hacks with Iterative DPO Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06649 - Physical policy gradient theorem for in situ stochastic-adjoint training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05808 - Robust Dynamic Expansion for Continual Learning under Backdoor Attacks via Purification and Selective Recovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06346 - Iterative Audio Separation with Mixture Consistency via MIMO Model Extension Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07226 - Kolmogorov--Arnold stability for discontinuous functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07240 - Leveraging Discrete Function Decomposability for Scientific Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.03032 - CUSP: Decomposable Collective Uncertainty for Multi-Agent Multimodal Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05708 - Vision: Data-Centric Anchoring for Robust and Interpretable Agentic AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08216 - Parameterized and Streaming Algorithms for Euclidean Fair $k$-Center Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06384 - Translation of Black-Box Clinical Prediction Models into Standalone Transparent Nomograms: Temporal External Validation in Heart Transplantation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07610 - Infrastructure-based Monocular 3D Vehicle Localization Framework with Experimental Validation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05523 - MOLE: Detecting Insider Threats in AI Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06966 - PPIM: Pennes Physics-Informed Mamba for Heat-Source-Conditioned 3D Bioheat Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06869 - Target-Independent Micro-Interventions for Predicting Training Response Across Language-Model Families Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08618 - Sector-Mean: Deterministic Initialization of K-Means Centroids via Angular Sector Partitioning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06468 - Let It Go or Learn to Self-Correct: Continuous Diffusion for Constrained Discrete Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09009 - Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08312 - Prevalence calibration as shortcut mitigation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07922 - MOAE: Multi-Objective Agent Evolution with Pareto-Preserving Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05992 - Machine Learning for Pre-Culture ESBL Risk Stratification to Guide Empiric Antibiotic Selection: A 12-Hospital Study of Enterobacteriaceae Cultures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05970 - Guiding Worker Self-Selection in Crowdsourcing Contests: An LLM-Augmented Algorithmic Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07749 - Geometry-Aware Bayesian Parameter-Efficient Fine-Tuning on the Stiefel Manifold via Stein Variational Gradient Descent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08354 - One Step, One Lead: Mitigating Higher-Order Interference in Multi-Domain Reinforcement Learning via Cross-Step Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06469 - GPU-Enabled Large-Scale Optimization Using Randomized Linear Algebra Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08136 - Kalman Delta Networks: Uncertainty-aware Associative Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07816 - Sub-6 GHz Over-the-Air AMC via Curriculum Fine-Tuned CNN-Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07726 - Training-Free Task Vectors for LLM Behavioral Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09054 - SeisBench DAS: A machine learning framework for Distributed Acoustic Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07558 - CAROL: Context-Aware Online Learning for Fuzzer Scheduling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06772 - Latent-MoE: Domain-Aware Mixture-of-Experts for PDEs with Multi-Regime Physics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07814 - PlayTrain: An Efficient Reinforcement Learning Framework for LLM-Generated Adaptable JavaScript Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09059 - Flexible Motion Generation from Language and Style References Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08032 - Learning to Price and Stock Under Contextual and Censored Demand Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06083 - Distillation as Probability Transport: Routed On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08337 - Rethinking One-Shot Federated Graph Learning: Training-Free Statistical Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06154 - TontaubeV1: Streaming Text-to-Speech with Hierarchical Codec Modeling and Bounded Context Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08703 - How Does Parameter Pruning Reshape DNN Representations? An Interaction-Driven Exploration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06483 - No-Regret Mixing of LRU and LFU with Optimal Switching Cost Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07566 - Routing Dense Layouts with History-Aware Offline Reinforcement Learning using LSTM Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08232 - Earth System World Model for What-If Simulations: A Case Study for Terrestrial Ecosystems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08855 - Statistical versus machine learning-based spatial interpolation of post-processed ensemble weather forecasts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07512 - Local gradient neural operator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07752 - Second-Order Smooth Planning with Optimal-Transport Bellman Smoothing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06484 - Fixed-Dimensional Latent Flow for Generating Variable-Size 3D Molecules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08333 - LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05955 - Leveraging Cardiac Imaging to Improve ECG-Based Detection of Chagas Disease in Resource-Constrained Settings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08582 - Input-to-State Stability Framework for Fully Distributed Primal-Dual Dynamics for Quadratic GNEPs Without Multiplier Consensus Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06983 - Sharp Structure-Agnostic Minimax Risk for Partial Linear Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07997 - The Oversight Gap: What LLM Safety Monitors Miss, and Why It Is Not Capability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07162 - How to Make the Gradient Mapping Small for Constrained Stochastic Min-Max Problems and Beyond Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08380 - FedRAW: Preserving Rare-Label Influence in Asynchronous Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07192 - Online Signature Verification Using Augmented Path Signature and T-Mamba Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08276 - When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08476 - ONE CYLinder: A Benchmark for Graph-Based Surrogate Modeling of Unsteady Bluff-Body Flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08947 - The OCUDU dApp Platform: An Open Runtime and E3 Interface for Real-Time AI-RAN Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07843 - From Synthetic Priors to Model Behavior: Structural Coverage in Tabular Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06912 - Deep belief networks are exact Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05572 - Distributed Lag Neural Additive Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07381 - SLA-Safe Energy Control for AI-Native NG-RAN Using Stability-Aware Constrained PPO Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05861 - A Machine Learning Framework for Predicting Restaurant Food Waste to Support Sustainable Food Management Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08078 - A Note on Scaling in Randomly Rotated Quantization and Its Connection to the CDEF +1 Pythagorean Relation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08759 - DRIFT: Removing Diffusion Watermarks by Deflecting the Generative Trajectory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08213 - Are Verifier Errors Independent Within a GRPO Group? Evidence from Qwen2.5 Rollouts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06386 - High-Magnetization Sampling at Low Temperatures: Ising Models and Bayesian Sparse Linear Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08873 - DUA-D2C: Dynamic Uncertainty Aware Method for Overfitting Remediation in Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.15876 - RoPE attention is an exact forward-pass gradient step with softmax intact Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06685 - When Retain Constraints Conflict: Mitigating Forget-Retain Interference in Tabular Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06786 - Strategic Doctrine Language Models (sdLM): A Learning-System Framework for Doctrinal Consistency and Geopolitical Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.14862 - Difficulty-Adaptive Tree-Structured Policy Optimization for Expanding Reasoning Coverage in RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08650 - Two-dimensional Taxonomy for N-ary Knowledge Representation Learning Methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.05626 - CLUES-WEASEL: No additional clues required to choose your time series clustering algorithm Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07606 - NeuCME: Toward Dynamic Multimodal Continual Learning via Neural Combinatorics of Multiple Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07009 - BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.09596 - LATS: Levy Adaptive Tree Sampling for Feedback-Driven Diverse Target Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06761 - Silver Rate Is (Almost) Optimal for Gradient Descent Acceleration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09152 - Layer-Wise Gate-Controlled Prompt Truncation in a Multimodal Chest X-Ray Classifier Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06590 - LLM Layers Immediately Correct Each Other Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07876 - Broken on Arrival: Silently Defective LLM Artifacts in Public Model Registries and How to Catch Them Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05881 - Data Efficient Sample Selection for In-Context Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06670 - Closed-Form of the Local Galactic Potential and Stellar Distribution Function from Gaia DR3 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09011 - Think Wider: Mitigating Latent Rank Collapse in Implicit Chain-of-Thought Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07406 - Support Topology and Gradient Mixing in Sinkhorn Layers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07954 - Memory in Deep Time-Series Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06006 - Novel hybrid protein scaffold gap filling using weighted machine learning ensemble, beam search, and mass-constrained reranking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05436 - SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis and Fluency Measurement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05850 - Tensor network representations of discrete maximum entropy distributions via mean polytopes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07184 - Geographically Regularized AUC-Maximizing Personalized Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08379 - ParetoTransport: Generative Optimization by Mass Transport Toward The Pareto Front Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07706 - Attention-Enhanced Deep Features with Heterogeneous Ensemble Learning for Glaucoma Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06699 - Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.22255 - Beyond Worst-Case Coreset Bounds for $k$-Clustering via Determinantal Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06394 - CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.25323 - Length Generalization for Transformers via Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08851 - Optimal Slice-Adaptive Tuning of Hybrid Slice Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08172 - PocketVE: Stable and Property-Guided Structure-Based Drug Design with Variance-Exploding Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08101 - Modal Logic Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.03491 - FMMO: Detecting the Divergence Between Local Attribution and Global Drift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06173 - Revisiting Spectral Representations in Generative Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08253 - Causal DAG Identification for Count Data via Poisson Thinning Structural Equation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06098 - FedGenSC: Federated Generative Semantic Communication with Channel-Aware Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08593 - Asymptotically-informed neural networks for Black-Scholes implied volatility computation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05491 - Contextual Observer Grounding: Evaluating Situated Spatial Reasoning in Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06880 - Matryoshka Hash Representations for Model-Aware Compact Semantic Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07276 - MoEMB: Scaling Universal Multimodal Embeddings with Efficient Mixture-of-Experts Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08663 - Nystr\"om Attention Matches Full Attention for Cross-Sectional Stock Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08106 - Functional Attentive Interpretable Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05846 - LatentMD: Benchmarking Markdown Boundary Failures in LLM-Generated Text Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06993 - HypLTSF: A Hyperbolic Geometric View of Multi-Scale Hierarchies for Long-Term Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08286 - EStream: Fast and Memory-Efficient MoE Prefill through Expert Virtualization on Mobile NPUs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06551 - AAMBERS-UAV: Acquisition-Aware Multimodal Backbone Evaluation and Ranking for UAV Weedy Rice Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05762 - MI-PEFT: Mixture-of-Experts Integrated Parameter-Efficient Fine-Tuning Protein Language Models Improves Acidophilic Proteins Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08059 - CausalBN-Bench: A Comprehensive Benchmark for Causal Learning Capability of LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2404.06349 - Physics-Informed Deep Learning for False Ventricular Tachycardia Alarm Reduction in the ICU Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08992 - Rollcast: Proper-Score Gated Rolling Anchors for Adaptive Probabilistic Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05561 - JEDI: JEPA-to-Edge Distillation for Efficient Cropland Segmentation from Satellite Imagery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07915 - AhaBench: Do Agents Learn from Prior Experience? A Benchmark for Long-Horizon Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05435 - Towards Bridging the Gap Between Offline and Iterative Alignment via Preference Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06893 - CircuitLens: Reasoning Circuits as Data Selection Signals for Reinforcement Learning with Verifiable Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07183 - CALM: Class-wise Agreement and Label-gated Disagreement Modulation for Decentralized Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05884 - Leveraging contextual events on structure-aware next activity prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08622 - Long-Horizon Language Model Reinforcement Learning via Progressive Point Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07303 - SIM: Subspace Interaction-based Method for Token-Level Text Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08200 - EigenLI: Spectral Approximations to Late Interaction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07561 - FANS: Federated Adaptive Network Search Learning for Heterogeneous Devices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06106 - Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09135 - EEG-Driven Decoding Framework for Passenger Hazard Perception in Highly Automated Vehicles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07128 - Hyperparameter Scaling Laws Across MoE Sparsity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08690 - Sparse Incident-Cluster Learning for 12-hour Port Flood Pre-warning in Digital-Twin Analytics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06109 - Robust conditional dimension reduction for dissimilarity data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06284 - Generation of Vectorized Maps Beyond Vehicle View Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07511 - Online Surrogate Repair: Decoupling High-Fidelity Feedback from Search Length in Closed-Loop Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07655 - Online Learning with LLM Experts from Limited Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05820 - Clean Accuracy Does Not Guarantee Provenance Robustness: A Prospective Codec-Stress Evaluation of Audio Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07981 - Deep Learning to Automate Parameter Extraction and Model Fitting of Two-Dimensional Transistors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.05134 - Feature Superposition in Neural Networks: From Theory to Practice Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06862 - NOAH: Learning the Full Patient Journey. A Longitudinal Multimodal Time-Aware Model for Representation and Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09140 - PhenoBench: Mapping What a Deeply Phenotyped Human Cohort Can Tell Us Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06080 - TASTE: Throughput-Aware Batch Size Tuning for On-Device Edge Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07444 - Certifying cooperation: a novel approach to cooperative multi-agent task generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06586 - Stability and Generalization of Straight-Through Estimators for Training Two-Layer Quantized Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06430 - AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06972 - CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08345 - A Specialized Large Multimodal Model for Interpreting PET/CT in Head and Neck Cancer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05532 - Deep learning from the crowd Fundamentals of morphological galaxy classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06316 - Streaming Hierarchical Inference with Tabular Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07956 - Continual Learning Mechanisms Compose for Long-Horizon Memorization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06986 - A Theoretical Analysis of Provable Compositional Generalization in Neural Networks: A Necessary and Sufficient Condition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.02627 - Graph neural networks and the energetic cavity method for combinatorial optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07456 - EgoNeMo: Transferable Map of Pedestrian Dynamics via Egocentric LiDAR Scan Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06195 - When and What to Teach: Budget-Aware Online Adaptation for Web Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05513 - CoRL: Co-Evolutionary Reinforcement Learning for Adaptive Indirect Prompt-Injection Attacks and Defenses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07529 - Fast PAC Global Optimization via Restarted Langevin: Exploration, Exploitation, and Degenerate Cooling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06196 - Optimal estimation for Functional Linear Regression with Noisy Discretized Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08671 - Data-driven rational function neural networks: a new method for generating analytical models of rock physics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2109.08813 - Robustness of LLM-Generated SystemVerilog Assertions to Semantics-Preserving RTL Transformations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05658 - On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via Hashing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07681 - Tracing Mathematical Proficiency Through Problem-Solving Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.00311 - The Dynamics of Generalization in Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.16450 - Evaluation of Contextual Understanding in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09004 - Limitations of Automated Simulatability: LLM Simulators Can Bypass Explanations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08585 - GIFT: Reconciling Post-Training Objectives via Variational Finite-Temperature Gibbs Initialization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.09233 - Connectome-to-Function: Conditional Generative Latent Representations for Reservoir Computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06093 - CAVEAT: Recurrent Multimodal Diffusion Planning for Mapless Aerial Exploration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06623 - Charts Are Beyond Pixels: Probing for Layer-Wise Chart Understanding and Editing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08657 - Noisy-Space Policy Gradient for Diffusion Policies in Offline Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06882 - Multi-label versus multi-class classification of blood cells and their aggregates in microfluidic channels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07410 - Learning Kernels by Alignment for Multiclass Bayes Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06474 - InfluenceField: A Differentiable Field with Interventionally Identifiable Causal Structure for Multimodal World Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07874 - ARC-Bench: Closed-Loop Replanning Masks Broken Action Ranking in Frozen JEPA World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05461 - Formation of structural attractors in neuromorphic systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06826 - Distribution-free inference on the number of changepoints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08234 - Diagonal Attenuation: A Finite-Sample Correction for PCA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05796 - Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07108 - Curriculum Learning as Transport: Understanding Curricula with Wasserstein Geodesics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09099 - A cautionary tale on the cost-effectiveness of collaborative AI in real-world medical applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.06494 - Emergent Charging Coordination in Electric Delivery Fleets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07689 - Best-of-Both Worlds for linear contextual bandits with paid observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.07424 - Constitutive State-Space Modeling of Path-Dependent Plasticity: A Resolution-Consistent and Parallelizable Computational Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07294 - QGB-W$k$NN: Quantum Granular-Ball Learning for Robust Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05952 - Steering Interference Reflects the Model's Defaults, Not the Behavior Directions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06951 - SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.08192 - LayerRoute: Action-Conditioned Mixture-of-Layers Routing for Vision-Language-Action Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06079 - Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07627 - Hidden in Plain Sight: The Overlooked Significance of Canonical Elements for Extreme LLM Sparsity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06557 - The Exact Time-Uniform Rate Frontier for Stochastic Gradient Descent on Smooth Convex Objectives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08537 - On BatchNorm Forward Modes in Value-Based Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06421 - Do Reviewers Still Reward Lexical Complexity? A Frozen-Rater Study of Preference Drift in 124K ICLR Reviews Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08475 - Heat Field Signatures: From Point Clouds to Smooth Geometry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07975 - Pre-Whitening and BCJR Posterior Distillation for Bi-LSTM Detection in Faster-than-Nyquist Signaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07762 - Ostrich: Taking Large Strides Through Stiff Contact in Differentiable Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08800 - HyperTransfer: Understanding the Equivalence between Base Optimizer and Hyperball Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07017 - Bayesian Matrix-Valued Graphs for Context-Dependent Multivariate Relationships Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08055 - EMBLEM: Enhancing Multi-script Table Detection through Masking Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.08330 - Steering Under Compression: Dose-Response, Capability Cost, and Failure Asymmetry in Quantized LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06473 - Physics-Informed Neural Networks for Depth-Averaged Granular Avalanche Dynamics on Curved Topography Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05542 - Squeeze10-LLM: Squeezing LLMs' Weights by 10 Times via a Staged Mixed-Precision Quantization Method Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.18073 - The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08901 - Contrastive Knowledge Distillation for Anomaly Detection in Multi-Illumination/Focus Display Images Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05520 - Particle Dynamics of Flow Matching and Classifier-Free Guidance from a Stagewise Geometry Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06947 - From Human Labels to Literature: Semi-Supervised Learning of NMR Chemical Shifts at Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.18524 - Compressed Recurrent Feedback in Tsetlin Machines: A Reproducible Boolean-FSM Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06133 - Sparse Data Augmentation for Optimization with Provable Guarantees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08133 - Stable-MM-R1: Anchoring Multimodal Reasoning Dynamics via Entropy-Guided Stratification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07148 - Introductory Notes on Learning$^2$ Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06546 - Speed Limit for Information Acquisition in Stochastic Learning Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08219 - KTO: Model Alignment as Prospect Theoretic Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.01306 - SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05533 - GraphNOSE: A Graph Transformer in Olfaction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05694 - Beyond the Matrix Sign: Quadratic Spectral Descent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07597 - Masking Radar Cognition under Adversarial Surveillance: A Distributional Privacy Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07428 - Latent-to-Latent Flow for Volumetric Stochastic Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07460 - Learning Metamaterial Eigenmodes with Wavelet-Encoded Fourier Neural Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08102 - Solving the Elastic Wave Equation with Physics-Informed Neural Networks: A Robust and Critical Assessment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07983 - HB-PVI: A Hierarchical Bayesian Personalization and Value-of-Information Framework for Complex Activity Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05582 - Accelerating Diffusion Transformers with Gaussian Process Rectified Feature Cache Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05981 - Fitting and Learning Basis-Restricted Propositional Formulas Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08961 - Newton Matching for Generative Modeling: A Unified Framework for Fine-Tuning and Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05727 - HealthLoopQA: A Context-Aware Question Answering Benchmark for Interpreting Wearable Monitoring Data in Diabetes Care Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06976 - BAFF: Bid-Aware Filter Family for Mitigating Training Data Interference in RTB A/B Tests Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08725 - Budgeted Task-Aware Acquisition of Dynamic Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05862 - A Statistical and Machine Learning Framework for Quantifying Offensive Impact in Professional Box Lacrosse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06610 - AVCG: A Generalized Variational Framework for Counterfactual Generation under Hypothesis Distributions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07917 - Semi-Supervised Learning under Spatially Biased Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07982 - Do Reasoning Representations Help Humans Evaluate LLM Outputs? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09038 - IXPLORE: Bounded Ideal Point Estimation with Grid-Based Uncertainty Quantification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06018 - Architectural and Regularization Components in Deep Learning Medical Image Registration: Systematic Ablation Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05484 - Inclusive electron-nucleus cross section models from domain adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08463 - On the Effectiveness of the z-Transform Method in Quadratic Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.03404 - A Quantitative Evaluation Framework for Temporal Explainability in Echocardiographic Video Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08043 - One Rate Is Not Enough: Adaptive Anisotropic Learning Rates for LoRA Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05885 - Spatial Attention Supervision for Defect Localization: Exploiting Ground-Truth Masks as Training Signal in Diffusion-Augmented Defect Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06232 - Parallelism Strategy Chaining for Fast Training Convergence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07236 - Robust Conformal Consensus: Multi-Agent LLM-as-a-Judge Interval Evaluation with Conformal Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06367 - The Accuracy Paradox: Empirical Diagnostic of Default Decision Thresholds in Multi-Label Enzyme Commission Prediction [With Code] Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07897 - Towards Unified Multimodal Graph Foundation Model: A Bridge-Router-Adapter Based Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06668 - Data Scout: Targeted Web Crawling for Domain-Specific Pretraining Corpora Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05766 - Accelerated High-Accuracy Sampling from a Warm Start via the Proximal Bouncy Particle Sampler Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06905 - Analysis of Respiratory Sinus Arrhythmia with Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05698 - Not Just Oversmoothing: Detecting the Echo Chamber Effect in Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06521 - Temporal-Causal Inference for Reinforcement Learning via Automata Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07461 - GraphFAS: A Distributed System for Automated Graph Feature Generation and Selection in Industrial Transaction Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08970 - Synergistic Fusion of Topological Structure and Temporal Semantics of Mobility for Urban Region Embedding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08268 - Beyond Task Success: Stage-Wise Reliability of World Model Planning under Sensing Degradation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07126 - Toward Sustainable Distributed LLM Inference: A Systems Synthesis and Research Agenda for an Energy-, Carbon-, and Cache-Aware llm-d Control Plane Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05565 - AGSA-Net: Abundance-Guided Self-Attention Network for Spectral Unmixing-Aware Hyperspectral Remote Sensing Image Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06359 - Steering Geometry: Validating Human Value Geometry in LLM Steering Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06289 - DISEIL: Demonstration Distillation for Sample-Efficient Imitation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08123 - TV-Regulated OPD: Direction Matters in On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08341 - Fusing Sequence Motifs and Pan-Genomic Features: Antimicrobial Resistance Prediction using an Explainable Lightweight 1D CNN-XGBoost Ensemble Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.23552 - A Review of the Long Horizon Forecasting Problem in Time Series Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.12809 - The Role of Uncertainty in Assessing the Fairness of Machine Learning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07959 - Iterative GRPO: Batch-Online Multi-Turn RL via Single-Turn RLHF Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.21638 - Spectral Prioritized Sweeping in Nonstationary Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06186 - MpSub: A Momentum $p$-Dimensional Subspace Trust-Region Method for Derivative-Free Fine-Tuning of Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07666 - Foundation Models for Generalizable Semantic and Goal-Oriented Communication Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07853 - Detecting and explaining clinical-omics inconsistencies to improve patient cohort stratification: an application to Parkinson's disease Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.03656 - Electricity Price Forecasting: Bridging Linear Models, Neural Networks and Online Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.02856 - Fine-grained Distributed Backdoor Attacks in Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07147 - Efficient Exploration Is Enough Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07575 - Role-Specific Predictive Geometries for Nonstationary Multivariate Graph-Signal Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06519 - Learning to build covering structures with continuous adjustments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08669 - Differentiable Causal Discovery for Singular Linear Models under Confounding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.01368 - From Proxies to Fields: Spatiotemporal Reconstruction of Global Radiation from Sparse Sensor Sequences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.12045 - Interpretable and Fair Generalized Additive Neural Networks via Multi-objective Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05946 - Minimum distance classification for nonlinear dynamical systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.04058 - Suan: Rectifying Direct Preference Safety Alignment in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08634 - SGD in Multiclass Logistic Regression: Sequential Learning and Scaling Laws Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07868 - IIns-VAE+: A Robust Transfer Learning Framework for Environmental Identification in Wireless Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06131 - RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07414 - Calendar-SPCA: Interpretable Representation Learning for Multi-Periodic Electricity Consumption Profiles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06060 - Benchmarking Storage Systems for Machine Learning Workloads Using NIO Bench Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05418 - Two-Scale Localized PCA-Net: Coarse-Global and Local-Residual Representations for Artifact-Reduced PDE Operator Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08034 - Constrained Bayesian Optimization for Hierarchical Federated Learning in IoT Networks for Plant Disease Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06830 - Distributed Dexterous Manipulation with Spatially Conditioned Multi-Agent Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06930 - PatchFormer: A Patch-Based Time Series Foundation Model with Hierarchical Masked Reconstruction and Cross-Domain Transfer Learning for Zero-Shot Multi-Horizon Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.20845 - SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.08999 - Power Mean Estimation in Stochastic Continuous Monte Carlo Tree Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06489 - CogniDir: Combating Cognitive Malicious Comments via Adaptive Distributional Learning for Robust Fake News Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.09712 - Large-Scale Pretraining for Improving Deep Learning-Based Geometric Distortion Correction of Diffusion-Weighted Imaging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06437