TILens Daily Edition 2026-08-18 Filters: topic=ai, github=hidden Stats: 1025 articles, 9 sources, 1010 research papers Top topics: AI, AI Research, AI Labs ## News - ChatGPT Ads expands across Europe Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/chatgpt-ads-expands-across-europe - Strengthening democratic oversight in national security Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/strengthening-democratic-oversight-in-national-security - How Much Memory Does Your Agent Actually Need? Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/ibm-research/altk-evolve-hmm - Partnering with CodeAI to prepare the first AI generation Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/partnering-with-codeai - Introducing ChatGPT for Teens: Built for learning, backed by protections Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/chatgpt-for-teens - Pacing model development in an era of cyber-critical capabilities Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/pacing-model-development-cyber-capabilities - Asana completed a years-long code migration in 2 weeks with Codex Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/asana - Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/multi-vector-encoder - How NVIDIA scales expertise with ChatGPT Work Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/nvidia/chatgpt-work - AI Traffic Now Converts 54% Better Than Everything Else. Many Sites Can't Be Read by It! Source: ai-agents-simplified Topic: AI (+AI Tools) URL: https://aiagentssimplified.substack.com/p/ai-traffic-now-converts-54-better - The $1.4T case against Meta Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/the-1-4t-case-against-meta - We still don’t know how people are really using AI Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/08/18/1142226/how-people-use-ai/ - AI’s recursive self-improvement might not come so quickly after all Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/08/18/1142188/ai-recursive-self-improvement/ - Cursor's Origin hits GitHub on its worst day Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/cursor-origin-hits-github-on-its-worst-day ## Research - Andy: A Mathematical Agent for Rigorous Proof and Autonomous Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15052 - Advanced modelling and data analytics in aviation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14746 - Unified Pedestrian Path Prediction Using Inverse Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15929 - Low-Rank Dynamics-Effective Latent Carriers for Counterfactual Rollout in Learned World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15156 - SCOPE: Score-Isolated Agentic Optimization for Video World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15043 - FactReview: Evidence-Grounded Peer Review with Execution-Based Claim Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.04074 - Demand-Driven Vertiport Siting and Discrete-Event Fleet Simulation for On-Demand Urban Air Mobility Network Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14974 - Position: Medical AI Neglects Real Treatment Outcomes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14598 - The Fragility of Strategic Thinking in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.10813 - Think Inside the Chunk: RegulaRAG for Regulation-Compliant Scenario Generation using LLMs: A Case Study of UN Regulation No. 152 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16394 - ML-AutoResearch: Training Machine Learning Research Agents with Automatically Generated Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.17216 - JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving Skills Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16465 - Securing AI-Generated Code: A Just-in-Time Vulnerability Detection and Remediation Pipeline Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16187 - StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15089 - FloodReasonBench: Benchmarking VLM Reasoning Segmentation for Embodied Flood Response at the Edge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15410 - Governance at the Boundary: How Agent Decomposition Degrades Policy Compliance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16055 - ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15546 - From Generalist to Specialist: A Context-Fusion Framework for Endoscopic Polyp Reporting with a Frozen VLM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15580 - Contrastive Energy Fields for Inference-Time Procedure Planning in Instructional Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16457 - VARM-Bench: Benchmarking Verifiable Structured Reasoning in Chinese Abusive Speech Moderation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15600 - EgoGazeLite: On-Device Egocentric Gaze Prediction for Token-Efficient Multimodal LLM Video Input Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15614 - Breaking and Defending LLM-Powered Social Media Bot Detection Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15893 - Looks Can be Deceiving: Annotator and Reviewer Performance Across Imagery Sources in Crowd-Sourced Aerial Damage Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14942 - AeroCopilotBench: A Two-Tier Benchmark for Evaluating LLM Agents as Aviation Copilots in an Interactive Virtual Cockpit Environment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16349 - When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16806 - What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14841 - Bias-Corrected Ceilings of Emotion Predictability from Human Label Variation Based on Instance-Level Fano Bounds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15619 - Noesis: Bidirectional Graph-RAG with Adaptive Parallelism and Cross-Knowledge-Base Semantic Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15919 - Afterlife Delegation Protocol: Speculative Design of Self-Sovereign Agents that Outlive Their Principals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15405 - A Policy Algebra for Trust-Preserving Agentic AI Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16402 - $D^{2}R^{2}$: Discrete Diffusion with Regulation Reinforcement for Single-Cell Perturbation Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15288 - A Human-Centred Approach to Benchmarking LLMs for Parenting Advice Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14622 - Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00270 - ParaTempo: Efficient Parallel Reasoning via Temporal Confidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16425 - PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15285 - DeCo-MIL: Debiased Counterfactual Reasoning for Long-Tailed Whole Slide Image Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14719 - Understanding AI Anxiety in the Workplace: A Multimethod Investigation Using Fear Acquisition Theory and the Technology Acceptance Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14609 - A Network-driven Framework for Public Event Forecasting via Dynamic Interaction Network Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15488 - DiffImaginE: Imagine to Verify Entity Types with Diffusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03025 - Cross-Sign Language Transfer Learning Using Domain Adaptation with Multi-scale Temporal Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16804 - Cost Scales with Change, Not Corpus Size: Incrementally Maintaining an Evolving Semantic Substrate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16621 - The Open-Strategy Dictator Game: Cooperation Under Mutual Transparency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14913 - Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15565 - CM-MAE: A Physics-Guided Cross-Modal Self-Supervised Learning Framework for Vision-Wireless Applications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15972 - FabriMAE I Trust Myself? Self-Evaluating VLA Action Generation with Markov Attention Entropy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16697 - Bridging the Gap between Labeled and Unlabeled Data via Unified Flow with Feature Memory Bank Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16681 - A concentration result for multilayer feedforward neural networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15335 - Revisiting the Performance of Generative Artificial Intelligence on Introductory Object-Oriented Programming Assessments: Insights from 2026 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16318 - RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05714 - Who Leads Now? Token-Level Modality Arbitration for Chart-to-Code Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15510 - SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11079 - DriveCache: Action-Aware Caching for Driving World Model Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16354 - A Machine-Learned Comorbidity Index Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17450 - FLOPs vs Real Work: The Importance of Replication in AI Efficiency Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14550 - Adaptive Post-Processing Drives Instance-Level Detection in Stroke Lesion Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16377 - Evaluating Agentic Code Repair Capabilities in Distributed Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14863 - Position: Certified Correctness in Neural Constraint Reasoning Requires Symbolic Integration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14569 - Task-Driven Three-Layer Distributed Scheduling for Emergency Earth Observation in Large Low-Earth-Orbit Constellations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14789 - LLM-Based Hierarchical Coordinated Control with Continuation-Aware Policy Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15041 - Comprehensive Benchmarking of Deep Learning Architectures for Lung Cancer Histopathology Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15915 - Broken Symmetry in LLM Refusal: Answer Release Is More Local Than Refusal Restoration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15772 - When Agentic Executions Fail: Detecting and Localizing Runtime Faults from Telemetry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14680 - Unaccountable Delegation, Fading Skills: Mapping the Risks of Workplace AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08601 - Measuring Reward Hacking and Reasoning-Answer Decoupling Under Position-Confounded Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15445 - ARENA: Automated Red-Teaming for Large Audio Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15578 - ReasonCast: Agentic Demand Forecasting with Selective Semantic Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15291 - Identifying Confusion Trends in Concept-based XAI for Multi-Label Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15731 - LongRCA Bench: Diagnosing Responsible Roles and Root Causes in Long-Horizon Agent Failures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15242 - SKILL: Self-correcting Knowledge-guided Iterative Large Language Model Agent for Logic Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14579 - Accuracy and Reliability of Large Language Models in Cosmetic Chemistry and Skin Health: A Benchmarking Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14631 - What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16852 - A Human-LLM Teaming Framework for Privacy Risk Analysis: An Illustration with CBDC-Based Welfare Schemes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16461 - UniDot: A Unified Network for Sequence Modeling and Feature Interaction in Large-scale Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16797 - MistyPilot: Enabling Social-Robot Control through Multi-Agent LLM Skill Orchestration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15549 - An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13221 - Implementation of a Metacognition Framework for Self-Awareness and Self-Regulation in Ensembles of LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15400 - Navigation-Informed Embeddings: Dense-Retriever Adaptation from Agent Search Traces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15956 - RAGas: Retrieval-Augmented Gas Optimization for Smart Contracts with Continuous Knowledge Integration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15857 - PaSTel: Anchoring Histology in Spatial Transcriptomics via Multi-Scale Hierarchical Bio-Prior Contrastive Pretraining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14924 - Competing at Every Price Point with Agentic Evolution over a Menu of LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16207 - DeepInsight II: One Trace from Benchmark to Robot Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16556 - HyMem: Hierarchical Context Management for Long-Horizon Agents via Information Isolation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15703 - Evaluating Multimodal LLMs across Text and Audio Modalities for Accessible Disaster Assistance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14651 - PAS-QFL: Personalized Ansatz Selection for Quantum Federated Learning under Client Data Heterogeneity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14995 - Context Is Not Authority: Structured Runtime Governance for Financial Market Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09025 - TDD-Agent: Test-Driven Reasoning for Code Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16742 - Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14590 - Graph Neural Assisted Actor-Critic for Latency-Efficient Edge Vision System Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16142 - Orbital AI Computing: Carbon Tradeoffs Across Satellite Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14557 - Frontier AI Forecasting Has a Measurement Problem: An Audit of Progress Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14903 - Global AI Regulations for FAIR and Ethics in High-Risk Use Cases: A Comparative Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14562 - Reasoning-supported Robustness Validation of Automotive E/E Components Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16421 - Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16889 - Synchronized Logit Steering: Real-world Steganography Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14697 - BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26182 - SysEvolve: An AI-native, safe, autonomous adversarial attack-defense co-evolutionary system Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15012 - Cross-Domain Industrial Fault Detection by Causal Mechanism Monitoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14666 - Second-Order Policy Effects as State Transitions: A Source-Linked Benchmark for Policy Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15101 - Hypergraph-based Multimodal Retrieval-Augmented Generation with Incremental Refinement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16628 - WeSCE: A Benchmark for Measuring Security Drift in LLM-Driven Code Editing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15092 - Specifying AI-SDLC Processes: A Protocol Language for Human-Agent Boundaries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20615 - A survey of AI-generated voices and their detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15411 - Handover Analysis for Vehicular Communication with Explainability on the Fly Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14820 - Identifying Harm in Personalized, Generative AI Systems Requires User-Centered Auditing at the Interaction Level Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14692 - Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15636 - Historical Backtesting for Scientific Question Discovery: A Protocol and Astronomy Pilot Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16795 - Learning Agent Execution for KV-Cache Management in Agentic Serving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14624 - Semantic Uncertainty-Guided Orchestration in Hierarchical Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14707 - PolyComp: A Polycube-based Benchmark for Compositional 3D Spatial Reasoning in Multimodal Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14741 - VCE-Skill: Enhancing Skill Self-Evolution with Version-Change Experience Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16544 - Assessing LLMs' mathematical abilities requires understanding the various mechanisms of mathematical creativity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16118 - Drive, Pack, Fly: The Travelling Thief Problem with Drone Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16435 - Beyond Thresholds: A Quality-Aware Decision Intelligence Framework for Cold Chain IoT Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15082 - VGGT-Align: Bridging Local Reconstruction and Global Consistency for Long-Sequence 3D Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15260 - A Shop Floor Production Scheduling Case based on RFID-supported Smart Factory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16626 - Decode-Branch Transformers: Decoupling the Primary Prefill Path from Additional Decode Computation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12385 - Bounded Semantic Planning and Deterministic Compilation for Reliable Enterprise Text-to-SQL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16663 - UAV Video Deblurring via Motion-Aware Diffusion: A Path to Robust Target Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15259 - SkillCommit: Evolving Agent Skills through Behaviorally Validated Scope Expansion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15165 - SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17648 - A Two-Stage Learning PINN Approach for Solving the Inverse Problem of the 1D Porous Medium Equation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16475 - MUSE: An Interactive Meta-Agent for Understanding and Steering LLM-powered Data Science Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16181 - WARA: Toward Automated Wireless Optimization Research with Closed-Loop LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14573 - FeatureHospital: A Skill-Driven Multi-Agent Framework for Automated Algorithm Customization in Multi-View Multi-Label Feature Selection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16148 - Hierarchical Adaptive Feature Refinement Network for VHR Remote Sensing Image Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15647 - Decoupled Temporal Encoding for Generative Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16274 - Position: AI Governance Needs ISO-like Interoperability Protocols, Not Just Laws Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14568 - Physics-informed VAE-EVT for Tail Aware Radio Map Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15314 - What Does Context Compression Cost an Agent? Interaction Costs Unrevealed by Task-Completion Metrics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16370 - Dynamic Evidence Collection Ecosystem for Assessment Integrity and Authentic Competence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16016 - A Temporal Reasoning Benchmarking Framework for LRMs via Difficulty-controlled and Dynamic Test Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04784 - BaT: Towards Self-Evolving Medical Research Agent with Stage Rubrics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16211 - A Regulatory Placebo? The Systemic Failure of Mandatory GenAI Labeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16470 - Walk Before You Run: The Importance of Data Exploration for Data Analysis Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16045 - RRFC: Recursive Refinement via Feedback Conditioning for Iterative Image-to-Image Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15694 - Synthesizing Post-Acetazolamide Cerebral Blood Flow Maps from Baseline MRI in Moyamoya Using 3D Generative AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14758 - Auditing an AI-Generated Mathematical Proof: A Correction to a Greedy Conditioning Lemma in Quantum Parallel Repetition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14673 - GraphLoom: Reliability-Calibrated Graph Evidence Routing for Multimodal KG-RAG Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15056 - Argumentation for Common Ground: Finding Zones of Possible Agreement between Individuals in Conflict Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15634 - Characterising cardiac tissue properties with graph neural networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15843 - CUBICS: Situation-aware performance estimation for safety-relevant ML components Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16564 - From Contexts to Values: Context-Dependent Defeat in Abstract Argumentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15536 - MLLM-Guided Semantic Correction for Text-to-Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16513 - TwinGridShield: Consequence-Aware Runtime Authorization for LLM Grid-Agent Actions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15391 - TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16156 - Individual Disempowerment through an Advice Channel: Control Loss when Influence is Endogenous Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14795 - VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15265 - A Responsible Artificial Intelligence Framework for Groundwater Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15657 - CG-GLORE: A Conjugate Gradient-Based Global-Local Regularization Network for Sparse-View CT Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15246 - CardiacMamba: Fair and Robust RGB-RF Fusion for Remote Heart Rate Estimation via State Space Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15831 - Academic League of Artificial Intelligence - An Integrative Perspective of Teaching, Research, and Extension Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.13447 - Automating and Scaling Behavioral Scientific Research on AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10030 - Funnel of Thoughts: Efficient Test-Time Scaling via Early Voting and Rollout Pruning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15065 - Picking the Right Image to Classify: Reliable-Input Selection in Teledermatology Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16198 - Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03988 - Task- and Session-Level Model Routing: A Common-Interface Hybrid Evaluation of Four Open-Source Routers Across Four Benchmarks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14641 - Towards Risk-free AI Agent Deployment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16411 - CACSurv: Concordance-Aligned Comparative Learning with Large Language Models for Cancer Survival Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16594 - Towards Standardized Evaluation in Automated Domain Modeling: Introducing a Benchmark Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15255 - An Evaluation Framework for National AI Regulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15417 - RLCascadeRouter: Quality-Estimator-Free Cascade Routing via Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15817 - LongDocBench: Benchmarking TOC Hierarchy and Contextual Relationship Recovery in Long Documents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15064 - PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16637 - Beyond Asking: A Pipeline for Personalized Game Generation that Reads Players from Behavior Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16196 - Do LLM Agents Negotiate Rationally? A Mechanism-Design Framework for Verifiable Multi-Agent Interaction over A2A/MCP Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14613 - Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14825 - ALKEMIE Agent: an autonomous platform for computational materials design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15776 - Pre-training Visual Dexterity in Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15917 - Generated Context versus Governed State: Functional Conditions for Accountable Longitudinal Clinical Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14804 - ENAF: A Multi-Exit Network with an Adaptive Patch Fusion for Large Image Super Resolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15349 - Dynamic Multi-Byte Prediction With Hierarchical Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15454 - Orbit-Planner: Towards Latent World Models for On-Orbit Obstacle Avoidance of Satellite Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16651 - Time to Reason: Scalable Neurosymbolic Learning for LTLf via Fuzzy Semantics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16443 - The Unwritten Benchmark: A New Challenge for Multimodal Machine Learning in Abstract Perceptual Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14558 - Pricing the Risk of Runtime Compression: Anytime-Valid Admission and a Served-Output Law for Compressed Serving State Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15810 - The Authority Resolution Framework: A Five-Domain Ontology for Governing Who and What Decides, at Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15832 - The Value of a Prompt: An LLM-Relative Kolmogorov-Complexity Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16438 - Bounded Agents: Delegation Security for Multi-Agent AI Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15888 - Process-Constituted Intelligence: A Shared Criterion for Humans and Machines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16213 - MedMCP-Calc: Benchmarking LLMs for Realistic Medical Calculator Scenarios via MCP Integration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.23049 - Max-Q Selective Imitation for Human-in-the-Loop Online Robot Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15088 - JarvisBench: Always-on Intelligence Between Humans and Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14870 - Intelligent Base Station Deployment in Urban Wireless Networks: A Geographic Data-Informed Digital Twin Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14599 - Catching Hallucinated Citations in Video-LLM Question Answering: A Self-Verification Pipeline and Verifier Ablation Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15574 - Valhalla: A Layered Knowledge-State and Service-Governance Framework for Long-Term Scientific Knowledge Work Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15193 - GSBF: Gaussian Splatting for Environment-Aware Beamforming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05896 - ACTS-SQL: Agentic and Critic-Oriented Tree-Structured SQL Correctness with Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15145 - Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16791 - Physiological World Models for Human State Transitions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15309 - NebulaVLA: A Dual-Frequency Vision-Language-Action Model With Guide Action for Robotic Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16503 - MotionGS-SLAM: Event-Modulated Gaussian Splatting for Motion-Blur Robust SLAM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15024 - Robo-Dopamine 2.0: History-Conditioned and OOD-Aware Process Reward Modeling for Robotic Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15680 - S2-MoE: Enabling Efficient Self-Speculative Decoding for Mixture-of-Experts on Edge Devices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15018 - TAHB: A Comprehensive Benchmark for Text-Attributed Hypergraph Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15055 - Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15475 - Position: Evaluations of AI Moral Reasoning Still Miss Half of the Picture Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14566 - UC-PSRO: Utility-Conditioned Policy-Space Response Oracles with a Communication-Dropout Curriculum for Game-Theoretic Course-of-Action Generation in Adversarial Swarms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15372 - RETRACE: Resilience-Guided Trait-Conditioned Craving Estimation from Wearable Physiology in Opioid Use Disorder Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14947 - AudioTQ: A Data-Oblivious 6-Bit CPU Audio Codec via Randomized Hadamard Rotation and Lloyd-Max Quantization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15369 - GaussMemory: Task-Driven 3D Gaussian Scene Memory for Long-Horizon Robotic Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14986 - LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16763 - From Doyle to AGM: A Survey and an Implementation Roadmap for Belief Change Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14567 - Chronocooked: A Benchmark for Implicit Interval Timing in Reinforcement Learning Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16666 - Skill Blocks: How Should an Agent Load Its Skill? A Caching-Correct Comparison of Pre-load, On-Demand Tool-Loading, Progressive Disclosure, and Hybrid Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14943 - Intent-Driven Situation Tracking for User-Centric Multi-Turn Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15755 - Small Models Scout Bottleneck Order for Large-Model Data Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14936 - CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16246 - Decomposing Staleness in Recommender Systems: A Dual-Filter Framework for Supersession and Decay Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15780 - Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15591 - HarmTrace: Anchor-Calibrated Decoupled Optimization for Fine-Grained Target Identification in Harmful Memes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16622 - Information-Theoretic Causal Modelling of Semiconductor Process Dynamics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14678 - HaReCAP: Habitual-action Grounding for Recursive Large Language Model Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16447 - Measuring Obedience to Authority Across Large Language Models with the Milgram Paradigm Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16177 - LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15175 - Efficient Block-Layer Parallel Inference for Vision-Language-Action on Hybrid Architectures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14586 - Visible Reasoning and Indirect Prompt-Injection Monitorability Across English, Tamil, and Tanglish Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15392 - Kozuchi Agent: A Language-Agnostic Open-Weight Agent for Software Repair Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15579 - Incoherent by Design? On the Moral Self-Consistency of LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15354 - Position: Want Better ML Reviews? Stop Asking Nicely and Start Incentivizing with a Credit System Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14571 - Divergent-Convergent Reasoning: Scaling Test-Time Compute through Structured Solution Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15303 - Extend the Safety Horizon for Intelligent Transportation Systems through Semantic-Aware Cooperative Perception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14603 - Defake-o3: From Speculative Rationales to Verifiable Evidence for Explainable AIGI Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16259 - Runtime Observability for Heterogeneous Attention Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05863 - Synthetic Data Augmentation for Satellite-Based Analysis of Battle-Damaged Agricultural Fields in Ukraine Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16380 - The Benchmark Trap: Structures of Power and Injustice in AI Evaluations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15326 - Visualizing Uncertainty-to-Action Composition for Human Oversight Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16428 - Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16391 - Budget-Aware Tool Use Enables Effective Agent Scaling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.17006 - Artificial Intelligence as a Tool for Combating Child Labour: A Real-Time Edge Vision Pipeline for Child Detection and Age Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14770 - Quipu: A Governed Bitemporal Knowledge Graph Store Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16813 - X$^2$Localizer: Cross-grained Alignment for Progressive Cross-view Video Geo-localization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16658 - Toward AI-Friendly Cartography: Understanding How Color Design Influences Foundation Model Spatial Reasoning on Sequential Choropleth Maps Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15736 - Does the Proof Prove It That Way? Faithful Formalization of Elements Proofs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15432 - Agentic Data Cleaning Without a Clean Reference: An Experimental Study of Capabilities and Trade-offs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14765 - Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.06628 - Calibrated Generative AI as Meta-Reviewer: A Systemic Functional Linguistics Discourse Analysis of Reviews of Peer Reviews Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.15035 - Large Language Models Show Metacognitive Sensitivity in Medical Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14552 - Understanding Cognition-Induced Risks in Agentic AI Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15304 - Translating finite-domain integer constraint models to CP/SMT/ILP/PB/SAT solvers with CPMpy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15143 - Unsupervised Anomaly Detection for Image Dataset Quality Assurance in Multi-Center Breast MRI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16725 - MoE Router-Guided Clustering for Heterogeneous Federated Instruction Tuning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15311 - EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15502 - A cross-modal generative model for incomplete and degraded prostate MRI with multicentre clinical validation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16233 - The Synthetic Web: Adversarially-Curated Mini-Internets for Diagnosing Epistemic Weaknesses of Language Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.00801 - TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16765 - Platform Adaptation Under Governance Interventions: Actor Best-Response Modeling and an External Public-Case Benchmark Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15131 - HiPHI: A Large-Scale Benchmark for High-Precision Human Motion and Object-Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16222 - The Quality of Claude AI-authored Python Tests Is Not Weaker Than Human-authored Tests Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15188 - Euclid-Omni : A Unified Neuro-Symbolic Framework for Plane Geometry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14585 - MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15006 - GRIP: Grounded Reasoning via Information-Restricted Premises Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16776 - Static Pruning Across Sparse Retrieval Regimes: What Transfers, What Breaks, and What Still Helps Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16309 - SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.09105 - Large language models as synthetic clinical experts to inform longitudinal rare-disease modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16507 - GoalEvolve: From Handcrafted Algorithm Priors to Goal-Driven Evolution of Physical Design Algorithms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16733 - Mental Model Management: An Operator-Based Framework for LLM Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15451 - Beyond Pass@k: Measuring Reliability and Security of Agentic Code Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14711 - Beyond Correctness: Toward Automated Novelty Verification with Lean 4 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14669 - Chameleon: An Adaptive AI-Driven Honeypot Architecture Using Threat-Calibrated Particle Swarm Optimization and Semantic Deception Rapidly-Exploring Random Trees Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15407 - RISE: Roadside Infrastructure Sequence Understanding across 3D Tracking and Structured Vision-Language Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16480 - Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16578 - Decoupling Parcellation from Classification: Systematic Benchmark of Fast Brain Segmentation Methods for Alzheimer's Disease Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16039 - CETalk: Continuous Valence-Arousal Control for Audio-Driven 3D Talking Head Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15110 - Multi-Agent Closed-Loop Reasoning for Organic Structure Elucidation from Multimodal Spectra Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14720 - BRA-Audit: Budgeted Runtime Auditing for LLM Multi-Agent Systems via Cumulative-Exposure Audit-Point Placement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14668 - Beyond Direct Access: Resource Hijacking in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15108 - MELD: A Protocol for Merging Knowledge Across Distributed Agentic Memories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16357 - FZ-VLM: A Two Stage Florence-Zephyr Vision Language Model Framework for Pulmonary Nodule Characterization and Clinical Decision Making Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15004 - Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14667 - EA-LiteUNet: An Edge-Adaptive and Resource-Efficient U-Net for Boundary-Sensitive Dermoscopic Image Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15537 - MUPA$^{2}$E: Multimodal Unified Perception with Asymmetric Attention for Emotion Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15999 - Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15877 - Local AI pre-screening for human triple-blind peer review in health sciences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14625 - Adaptive Mixing of Policies from Searching and Policies from Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15700 - Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15389 - AstronOS: A Unified Execution Model and Runtime for Long-Horizon Agentic Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16381 - Software Engineering for AI-driven Building Operation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16237 - Augmenting Text to Increase Translation Difficulty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15932 - SpIn-ViT: Designing a Sparsity-Induced Vision Transformer That Is Mechanistically Interpretable Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14922 - Large Language Models and their Awareness of Mechanics and Spatial Geometry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14615 - From Reactive to Autonomous: Evolution of AI Operations in Cloud Network Infrastructure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14574 - When Is an Agent Evaluation Over? Outcome Finality and Cross-Unit Separation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14940 - When Entropy Is Not Enough: Reclaiming Lost Semantics in LLM Output Length Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15592 - OGX: An Open-Source, Vendor-Neutral Generative AI Application Server Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14580 - An Agentic Framework Using Rules and LLMs for Embedding and Annotating Descriptive Document Layouts: A Plant Science Use Case Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14587 - A Unified Backbone--Expert Framework with Relation-Token and Residual--Classifier Interfaces for Automatic Modulation Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15160 - Constraint-Aware Synthetic Tabular Data Generation via Inter-Column Constraint Discovery with LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15109 - Constitutive Priors for Machine Intelligence: A Legitimacy Theory of the Artificial Physical World Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15147 - HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16837 - A Temporal Planning Framework for Disruption Aware Dynamic Route Optimization in Heterogeneous Railway Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.14582 - SIGMA-Lane: Scale-pyramId Gated MAmba for Temporally Consistent Video Lane Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16338 - UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15930 - TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15594 - Hierarchical Agentic Incident Response with Digital-Twin-Validated Attack Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15016 - When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16801 - CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14791 - AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11216 - THESIS-MoE: Trainable Hierarchical Extraction and SteerIng of Sycophancy in Mixture-of-Experts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15687 - Baseline-Relative Counterfactual Refinement for Bit-Aware Visual Token Communication Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16192 - Validation-Frontier Representation Selection under Constrained Observation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15095 - Agent-Native Telemetry: Verifiable State-Delta Evidence for Autonomous Operations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16178 - When Do LLMs Apply the Wrong Law? Diagnosing LLM Failures in Temporal Legal Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14610 - ALPS: Measuring Valid Creativity in Large Language Models with Mathematical Construction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15979 - Trajectory-Level Automatic Curriculum Learning for Legged Locomotion on Unstructured Terrain Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16164 - OTel: Building Domain-Specialized Telecom LLM Foundations for Intelligent Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15436 - Audio-Visual Segmentation via Depth-Guided Collaborative Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16285 - Topological Attribution Distance (TAD): Revealing Segment-Level RAG Influence on LLM Output Geometry for Incident Log Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16775 - From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15127 - Generative data assimilation highlights fronts as key regulators of ocean energy cascade Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14955 - Position: AI Lock-In Is in Progress, and We Must Be Prepared Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14565 - ReForge: Keeping ABR Algorithms Never Finished with Verified Large Language Model Edits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15138 - NumerosityVLM: A Cognitively Inspired Benchmark for Interpreting Numerosity Representations in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15425 - Diagnosing Dense Same-Class Attribute Misbinding in Large Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16805 - Agent Inheritance Protocol: Speculating on Feralized Agents After Principals Die Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15403 - Grounding Healthcare LLMs in a Causal Knowledge Graph: Framework, Metrics, and a Cardiovascular Pilot Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15382 - A Comprehensive Survey of Wireless Foundation Models for AI-Native 6G Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14694 - When Less Is Enough: Context Selection and Prompting Strategies for Bengali News Headline Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15879 - Misconception Diagnosis From Student-Tutor Dialogue: Generate, Retrieve, Rerank Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02414 - IndicQE-APE: A Benchmark for Quality Estimation and Automatic Post-Editing for Indic Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16344 - LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.07449 - Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15008 - DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Decoupled Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.11603 - Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11621 - 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 - ChartFI: Benchmarking Faithfulness and Insightfulness of Chart Descriptions from Multimodal Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23694 - Does generative AI supersede supervised XMLC? A Benchmark Study on Automated Subject Indexing with German Scientific Literature Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.14882 - What to Forget in Unlearning? Forget Set Curation for Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14855 - Dense Expands, Sparse Anchors: Channel-Asymmetric Query Expansion for Hybrid Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15851 - MechMath: Sorrifier-Driven Formal Decomposition Workflow for Automated Theorem Proving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.24465 - QUMem: Personalized Memory for Query-Conditioned User-State Inference in LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16168 - Train Yourself as an LLM: Exploring Effects of AI Literacy on Persuasion via Role-playing LLM Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.02637 - Language Models Compare Quantities Using Number-specific and Unit-specific Heuristics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03982 - Scaling Manual-Grounded Appliance Manipulation with Data Synthesis and Unified Planning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15863 - Trust Is Not Enough: Influence Calibration for On-Policy Self-Distillation in Agentic RL Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14945 - The Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code Context Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14838 - AWED-PIPER: Agents, Web Applications & Expert Detectors for Personally Identifiable Information Protection & Fine-grained Named Entity Recognition across 36 languages for 6.6 Billion Speakers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.10161 - Multi-Modal Generative Fuzzy System: Fuzzy Inference Guided Large Model Interactive Question Answering Framework Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14584 - Characterizing Rhetorical Misalignment in Decision-Making with Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14630 - Beyond the pale: Assessing prevalence and contents of extremist speech in LLM training data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14813 - Policy Iteration with Human Feedback: Bringing Post-Training RL to In-context Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16831 - How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14905 - Automatic or Controlled? Repetition Priming Reveals Divergent Processing in Base LLMs, Instruct LLMs, and Humans Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14681 - Aborted but Not Forgotten: KV-Cache Retention Breaks Rollback Consistency in Language Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15939 - Large Language Model Assisted Operational Monitoring for Battery Energy Storage System Integrated Power Distribution Networks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15396 - $R^3$-Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16033 - TRACE-BN: Transferring Bangla-English Tutoring Behavior to a Sub-1B Offline Language Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15223 - Evidence of conceptual mastery in the application of rules by Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.00992 - VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10875 - Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Representation Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.07195 - Sequential LLM Release Facilitates Manipulation in Regulated Markets Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.11496 - Semantic Lenia: Emergence of Homeostatic Solitons within the Semantic Space of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11657 - DanceOPD: On-Policy Generative Field Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.27377 - Subliminal Steering: Stronger Encoding of Hidden Signals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.25783 - Single-Round Vector RAG vs an LLM-Compiled Wiki: A Preregistered Comparison on a Small Multi-Domain Research Corpus Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18490 - Logical Embeddings for Argument Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15325 - CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.13387 - Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16514 - Structural Generalization on SLOG without Hand-Written Rules Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.26157 - Plausible but Not Valid: A Psychometric Audit of LLMs as Synthetic Survey Respondents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14606 - Lost in Adaptation: Layer-Selective Recovery of Temporal Reasoning in Video-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.11399 - ContextClaim: A Context-Driven Paradigm for Verifiable Claim Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.30025 - Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16645 - A Large-Scale Chinese Knowledge Graph-Text Alignment Dataset for Benchmarking Knowledge-Grounded LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.06039 - Where Does Retrieval Fail? Evaluating RAG Architectures for Agricultural Advisory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14886 - Agentic Test-Time Scaling for WebAgents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.12276 - QA-Merging: Query-Adaptive Reasoning via Layer Selective Model Merging Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.03506 - Leakage-Audited Benchmarking Reveals Limited Evidence for Cross-Subject Auditory-Evoked EEG Vowel Perception Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00865 - jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08384 - The Political Ideology of Large Language Models: Measurement, Inconsistency, and Persuasive Influence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.04171 - AutoMem: A Text-Gradient Recursive Self-Improvement Framework for Automated Memory Architectures Search Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14621 - I-CALM: Incentivizing Confidence-Aware Abstention for LLM Selective Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.03904 - When Your Agent Opens the Chat App: Agent-Controlled Search over Raw Chat Logs Rivals Structured Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12888 - NARRATE: A Multimodal Real-World Australian Driving Dataset for Human-Centred Explanations in Automated Driving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14767 - When AI Rewrites, Classifiers Relax: Uncertainty-Aware Sentiment Analysis on Sarcastic and AI-Paraphrased Social Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15338 - Writing Style Similarity Reflects Academic Genealogy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14843 - Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.04120 - Gated Against One Model, Open to the Next: Option-Only Solvability in Legal Multiple-Choice Benchmarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15428 - When Stories Evolve: Benchmarking LLM Storytelling Across Agent Architectures in Open-Ended World Simulations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15654 - Wiktionary as a Crowdsourced Lexicon for English Dialects Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15641 - LENS: In-Context Search via Latent Evidence Exploration over Dynamic Raw Documents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16185 - Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12652 - The First ChineseBabyLM Challenge: training data-efficient and cognitively plausible language models for Chinese Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10745 - Propaganda Forensics: Recovering the Generation Pipeline of an AI-Driven Influence Campaign Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15746 - On the Role of Directionality in Structural Generalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.02307 - HalluTracer: Hallucination Detection via Depth-Averaging Truth Signals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16353 - Hallucination Span Detection with Input-Side Evidence Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15804 - Handoff-H1: An Orchestrated Vision-Agent System for Material Quantity Takeoff from Construction Blueprints Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15032 - Closing the Affective Loop: Multimodal Speaker-Listener Emotion-Dynamics-Aware Empathetic Social Robots Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16686 - CAPO: Constraint-Aware Prompt Optimization for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16068 - Using the Mimi codec for metalinguistic representations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15799 - FTA-Mem: Fact-Time-Affect Anchored Memory for Low-Density Long-Term Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16303 - Listen, Reason, and Segment: Aligning LALMs with Editorial Judgment for Media Chapterization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16539 - Executable Code Knowledge: Code as a Native, Validation-Carrying Knowledge Representation for AI Coding Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16295 - Model Hypnosis: Strong control of AI via additive subliminal effects Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16834 - LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06087 - Iterative Self-Learning for Expressive Text-to-Speech Synthesis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15910 - The Granularity Gap: A Multi-Dimensional Cross-Generational Audit of Sycophancy in Gemini Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05183 - Unadapted Multilingual ASR on a Garrusi Kurdish Evaluation Set: A Common-Reference Staged Normalization Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16379 - SocialCoach: Personalized Social Skill Learning with Agentic Tutoring and Practice Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04155 - 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 - jina-vlm: Small Multilingual Vision Language Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.04032 - The Commercial Tax: Rent-vs-Own Blind Spots in Multi-Hop Retrieval Benchmarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16096 - VTInstructor: Visual Trajectory Prompting for Navigation Instruction Generation in Continuous Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15284 - Analyzing Speech Condition Effects in Dysarthric ASR: A Layer-wise Probing Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01865 - Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16647 - BiAxisBias: Evaluating LLM Bias Beyond a Single Prompt and a Single Explanation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09041 - PolyDebate: A Game-Orchestrated Multimodal System for Debate Skills Practice and Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16276 - A validity-guided workflow for robust large language model research in psychology Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.04491 - $x$-Prediction Flow: Efficient Continuous Decoding for Masked Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29066 - Where did the ambiguity go? Examining how multimodal models interpret polysemous words Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00410 - Why Summaries Turn Neutral: Policy Attribution for Sentiment Drift in Reinforcement Learning from Human Feedback Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15530 - Token Distribution versus Data Volume: Domain Balancing in Multi-Domain Meeting Summarisation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15935 - Multimodal Language Models Benchmarked Against the NRC Reactor Operator Licensing Examination: Fine-Tuning and Retrieval Strategies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22067 - DYNASHIELD: A Black-Box Moving Target Defense for LLMs via Dynamic Decoding Customization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.07672 - Do Assessment Instruments Measure the Same Thing for Humans and LLMs? A Latent Structure Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15630 - HarmProfile: Characterizing Harmful Distributions in Frontier LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14577 - DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16053 - Mitigating Bias in Locally Constrained Decoding via Tractable Proposals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01926 - Deep Thought Alignment: Trajectory-Level Latent Distillation for Video Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16316 - Step-Level On-Policy Distillation: Interpolating Between On-Policy Distillation and Supervised Fine-Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16333 - Coverage Is Not Containment: A Fundamental Limit of Admission-Time Defenses Against Coordinated Poisoning of Vector Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16044 - DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.14107 - When Do Explanations Help In-Context Learning? A Comparative Study of Natural Language Explanation Types and Faithfulness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16627 - SymbolicLight V1: Spike-Gated Dual-Path Language Modeling at High Activation Sparsity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21333 - Prior Audit-Repair Context Shifts LLM Verifier Thresholds Toward Leniency Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16003 - Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21037 - D2-ScaleAgent: Dual-Dimensional Scaling for Long Document Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16417 - From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16002 - ReRef-3D: A Benchmark for Spatial Referring Expression-Guided 3D Scene Rearrangement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16011 - When Do Concepts Become Functionally Sufficient During Language-Model Training? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15323 - Reasoning-Based Personalized Generation for Users with Sparse Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.21219 - TaoLive Digital Avatar Agent Technical Report: Training Agents to Evolve with Their Harness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15763 - Beyond Tokens: A Survey on Decoding Methods for Large Language and Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14797 - PolyWorkBench: Benchmarking LLM Agents for Cross-Lingual Long-Horizon Workflows Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.06008 - Does a Tool Result Carry More Authority Than Plain Text? Three Prospective Studies of False-Claim Adoption in a Synthetic Assignment Task with Claude Opus 5 Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14992 - Language Models that Think, Chat Better Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.20357 - DSPrompt: Dynamic Soft Prompt Defense Against M-RAG Corruption Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16536 - Computational KJ-Ho: An Analyst-Bias-Free Insight Extraction Framework from Large-Scale Qualitative Data Using Domain-Specialized LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16467 - Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16554 - DeMTS: Denoising Trajectories as Multivariate Time Series for Hallucination Detection in Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14632 - Vision Language Models Cannot Plan, but Can They Formalize? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.21576 - MobileMem: Learning from a Year of Mobile Experiences Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.13606 - Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16868 - Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23811 - PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.09521 - KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15797 - Wiola 13M, a Gated Spiral Attention Architecture for Parameter Efficient Small Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14604 - Enhancing Science Classroom Discourse Analysis through Joint Multi-Task Learning for Reasoning-Component Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21137 - One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12253 - BengaliMCQ: Automatic Generation and Answer Prediction of Academic Multiple-Choice Questions in a Low-Resource Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15547 - Bactrainus: Optimizing Large Language Models for Multi-hop Complex Question Answering Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.06286 - PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16650 - MoRFI: Monotonic Sparse Autoencoder Feature Identification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.26866 - Bye-bye, Bluebook? Automating Legal Drudgery With AI-Augmented Rule Following Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.02763 - mR$^2$AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.15041 - LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07370 - Large language model-assisted discovery of cohorts from scientific literature Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15909 - Inference-Time Mitigation of Adversarial Political Bias in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14629 - Beyond Single Object: Learning 3D Relations with Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15710 - SEER: Long-Context Reasoning via Selective Visual-Text Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15962 - Semantic Space of Parts of Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15443 - BridgeAlign: Bridging Preference Alignment for Humanities and Social Sciences Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27366 - Why Vision Fails as a Universal Bridge: Rectifying Modality Asynchrony in Multilingual MLLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15085 - FollowUpBot: An LLM-Based Conversational Robot for Automatic Postoperative Follow-up Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.15502 - STAGE: Controlled Objective Admission for Multi-Preference LLM Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16553 - Class Imbalance and Batch Effects in LLM-Based Screening for Systematic Reviews Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14737 - EgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12627 - GALA: Generation-Aware Cross-Modal Alignment for Text-to-Time-Series Synthesis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.13741 - Demographic Injection in Medical Language Models under Diversity, Equity, and Inclusion Prompts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15254 - BabelSteering: Multilingual Safety Alignment via English Steering Vectors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16577 - Path2ST: Hierarchical Cell-Tissue Grounded Cross-Modal Translation for Spatial Transcriptomics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14710 - Counting Documents Is Not Counting Text: Unit Bias in Web-PDF Corpus Statistics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16390 - A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15102 - Skill2Query: Exploiting Skill Structure to Generate Pseudo-Queries for Agent Skill Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16071 - PLSQLBench: Benchmarking LLM Systems for Executable Procedural Database Programming Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15931 - Douyin Multimodal Embedding Model Technical Report Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02148 - A Pilot Study of Autocompleting Tokenizers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15080 - LLMs Get Smarter from Targeted Synthetic Multilingual Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15964 - Neurosymbolic Embodied Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16794 - When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16515 - Do Value Vectors in Deep Layers Need Context from the Residual Stream? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02780 - Faster, Cheaper, More Accurate: Specialised Knowledge Tracing Models Outperform LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02830 - Schema-Agnostic Graph Reasoning Agent for Hybrid Knowledge Graphs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15834 - MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15844 - STAIR: Semantic-Temporal Automaton for Interpretable Reasoning in Temporal Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16224 - Efficient Code Embeddings from Code Generation Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.21290 - CulTrace: Tracing Internal Cultural Reasoning in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.08879 - Domain Agnostic Text Redaction from Natural Language Rules using Instruction Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14693 - The Machine's Internal Clock: Do LLMs Share Human Temporal Illusions? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15394 - The Hallucination Snowball: Modeling Error Propagation as State Transitions in Multi-Agent LLM Pipelines Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14588 - VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14718 - Time as Structure: Temporal Dependency Graphs for Verifiable Deadline Computation over Legal Documents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15270 - From Prompts to Constructs: A Dual-Validity Framework for Large Language Model Research in Psychology Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.16697 - Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15071 - Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15022 - When Self-Consistency Backfires: Majority Vote Hurts the Majority of Hard Science Problems for Small LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11403 - Semantic Bandits: In-Context Exploration-Exploitation is Biased by Semantic Priors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16707 - Hypergraph as Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21858 - HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13964 - Discovering Conceptual Metaphors Across Topics and Media Types Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06652 - Does the LM Head Create a Harmful Gradient Bottleneck? A Causal Test Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16671 - A Cognitively Motivated Multidimensional Framework for Evaluating Metaphor Explanations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15828 - RamseyGadgets: A Graph Construction Dataset for LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14999 - From Positionwise Confidence to Prefix Scheduling: Verifier Skipping in Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14787 - DA-RAC: Distance-Aware Calibration of LLM Judges for Trustworthy AI Auditing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14950 - Personalized Auto-Research: Towards a True AI Co-Scientist Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14881 - HyperSkill: Self-Evolving LLM Agents via Hypergraph-Structured Skill Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16114 - MCBench: A Multicontext Safety Assessment Benchmark for Omni Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05177 - Clause Encounters of the Third Kind: Can LLMs Replace Language Teachers? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16286 - INSPIRE: A Benchmark for Instruction-Aware Speech Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16203 - DualMiT-Net: Local-Global Transformer-Convolutional Fusion for Breast Mass Segmentation in Mammographic Regions of Interest Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15019 - Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.12147 - Learning Koopman operators for coupled systems via information on governing equations of subsystems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.01835 - Adaptive Optimization via Momentum on Variance-Normalized Gradients Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10204 - Uncertainty Identifies Difficult Samples Across Methods: A Multi-Task Study on a Heterogeneous Skin Lesion Dataset Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14768 - Density-Reweighted Entropic Optimal Transport: Decoupling Geometry from Sampling Density Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16506 - A Scalable Pipeline for LLM-Teacher Distillation Labeling: Work-Stealing Job Scheduling and Memory-Aware GPU Concurrency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15975 - Group ICA 2.0: Closing the Gap Between Subjects and Group Latent Decomposition with Copula-Linked Group ICA (CoLiG-ICA) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16029 - Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16072 - Foresight-England: Development of a National-Scale Generative AI Model of Electronic Health Records for Medical Event Prediction across the COVID-19 Pandemic Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16273 - RouteTS: Frequency-Time Routing for Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14682 - From Fixed Grids to Moving Particles:A Transferable Latent Operator for Fluid Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14120 - NRCD: An Open Database of Collegiate Running with Unified Performance Standardization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14776 - RecurrentGPT: Expressive Depth through Recurrent Modulation in Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15062 - An Adaptive Gradient Clipping and Noise Injection Mechanism for Differentially Private Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15153 - The Limits of Binding in Dual Encoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15971 - ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27924 - A Generative Deep Learning Workflow for Inverse Molecular Design of Fuels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.12075 - Uncovering Hidden Leptonic Correlations with Flow Matching and Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15042 - Generalised Transportability via Causal Abstractions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15645 - LUNG-KGMM: Knowledge-Guided Multimodal Learning for Lung Cancer Incidence Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14657 - ER-KANs: Efficient and Robust Kolmogorov-Arnold Networks for Data-Scarce Scientific Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14773 - Real-Time State-of-Health Estimation and Online Degradation Prognosis from Partial Battery Discharge Using Physics-Informed Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14764 - SubZero+: Efficient Zeroth-Order LLM Fine-Tuning via Large Learning Rates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15665 - Pallas: A Proactive KV Cache Migration Framework for LLM Inference in AI-RAN Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16477 - Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14929 - When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16502 - Integrating Persuasion Theory into the Epidemiological Modelling of Health Misinformation Spread on Social Media Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15689 - Language models suffer from a curse of ambiguity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15448 - Interpretable Cross-Lingual Alignment in Small Language Models: Probing Cultural and Pragmatic Reasoning in Japanese-English Bilingual LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14896 - Proteus: Incremental Memory Activation for Long-Context Sequence Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16844 - PathFinder: Joint Decompositions of Linked Multimodal Datasets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14951 - Characterization of Thermal Systems from Noisy and Low-resolution Measurements Using Dynamic Mode Decomposition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14581 - Directional Curvature from Armijo Backtracking: A Low-Cost Sharpness Probe and a Calibration-Free Learning-Rate Safeguard for Adam Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03998 - Do Language Models Consistently Encode the Current Year? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15507 - Learning Auditable Classifier Models: Source-Disjoint Tree Ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15725 - One-shot Robust Federated Learning of Independent Component Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.20532 - Spectral Certificates and Projection-DPP Rounding for Determinantal MAP Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19411 - WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.04608 - Amortised Post-Hoc Explanation with Exact Preservation for Dynamic Graph Anomaly Detectors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15559 - Benchmarking Quantum Machine Learning for Power-System Attack Detection: Evaluation Choices Decide the Outcome Before the Models Do Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15617 - FedADB: Class Anchor-Driven Dual-Branch Federated Learning for Mitigating Forgetting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15310 - Periodic Topological Deep Learning for Polymer Design and Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26833 - In-Context Source and Channel Coding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.10267 - Distinguishing AI-Generated Music from Edited Audio as a Hard-Negative Robustness Task Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14916 - The Note-Chord-Voice Framework: Structured Source Separation and Causal Inference for EV Charging Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14756 - An automatic-differentiation framework for time-lapse electrical resistivity tomography inversion of hydrologic dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14661 - p-Spin Glass Network Efficient Single-Batch Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14774 - On Cross-Validation for Hyperparameter Optimization of Deep Learning Image Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14705 - Annealed Softmax Greedy in Many-Armed Bayesian Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.31034 - Learning to Price with Persuasion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16699 - GEO-Flag: Detecting and Measuring GEO-Optimized Web Content Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16824 - Hide&Seek: Learning to Explain in an End-to-End Differentiable Network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16689 - TinyCast: Probabilistic Zero-Shot Forecasting with Computed Periodicity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15767 - Take it Personally: The Limits of General SSL Representations for Real-Life PPG Emotion Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14675 - The Trade-off Between Covariate Dependence and Latent Structure in Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16245 - Quantifying the Gap Between Laboratory Battery Test Patterns and Field Duty Profiles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16212 - SMOPD: Selective Token-Entropy Masking for Dirty-History Multi-Turn On-Policy Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14647 - Early Cycle Charge Trajectory Generative Prediction and Full Life Cycle Health Management of Iron-Chromium Flow Batteries Based on FlowBD-E1 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14637 - FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15602 - Evolving Executable Pipeline Programs for AutoML with Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16416 - Behaviour Is an Incomplete Measure of Reasoning Development: Cross-surface pre-arrival accessibility and the limits of developmental inference in a recurrent-depth reasoner Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16085 - Learning Multi-Timescale Interventions under Safety and Resource Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.03875 - Zero-Shot Instruction Following in RL via Structured LTL Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.14344 - From Errors to Proofs: Minimal-Core-Guided Repair for Neuro-Symbolic Constraint Solving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14771 - Sufficient Dimesion Reduction via Generalized Stein's Lemma Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15121 - Provably Efficient Personalized Multi-Objective Bandits with Proactive Conversational Queries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08410 - Not All Neighbors Matter: Understanding the Impact of Graph Sparsification on GNN Pipelines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.06952 - Macroeconomic Forecasting with Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.00890 - Lightweight Deep Learning-Based Channel Estimation for RIS-Aided Extremely Large-Scale MIMO Systems on Resource-Limited Edge Devices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.09627 - VirnyFlow: Optimizing ML Pipelines for Accuracy, Fairness, and Stability at Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.01584 - OceanLight: Efficient Global Ocean Forecasting via Geometry-Adaptive Unstructured Mesh Representation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16070 - A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.16183 - Learning symplectic model reduction based on an approximation theorem of symplectic embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04623 - Stitch the Fragments: One-Shot Hierarchical Federated Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.06404 - Toward Better Assessment of LLMs' Performance in Clinical Error Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16643 - Demo: Real-time Generative Multicasting with On-Device Intent-aware Semantic Decomposition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14600 - A Physiology-Informed Digital Twin Framework for Simulating Liver Health Progression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14969 - One Residual with Three Reuses: A Wristband Front End for Gesture Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16542 - The Quantum Shortcut: Complex Phase-State Dynamics Reduce the Optimization Steps of Sequence Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14691 - Free-Flow Class-Incremental Learning: Towards Robust CIL under Variable Class Arrivals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.02765 - From Lab to Reality: A Practical Evaluation of Deep Learning Models and LLMs for Vulnerability Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.10485 - EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2302.12177 - Not All Attention Is Equal: A Quantitative Survey of the EEI Trade-off Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15459 - CoupVisor: Strategy Optimization by Round and Challenge Decision Support Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15868 - SL-S4Wave: Self-Supervised Learning of Physiological Waveforms with Structured State Space Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19888 - Degradation-Aligned Self-Supervised Learning for State of Health Estimation of Lithium-Ion Batteries under Label Sparsity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16612 - Demystifying Oversmoothing in Sheaf Neural Networks: An Index-Theoretic Criterion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16180 - LiD-GLM: Lipschitz-constrained Deep Generalized Linear Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16340 - Technological Advances in Detecting and Managing Cognitive Impairment in Older Adults: Trends, Challenges, and Future Directions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28687 - Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.13341 - On the Principles Behind Neural Network Optimizers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16760 - Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14963 - The Optimal Sample Complexity of Multiclass and List Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.24749 - Decentralized Federated Learning for Heterogeneous Multi-Task Semantic Communication Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15256 - Data-Efficient and Interpretable Classification of Circulating Tumor Cell Phenotypes in Microfluidic Devices via Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16870 - Towards Unified Approaches in Self-Supervised Event Stream Modeling: Progress and Prospects Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.04899 - Structured Prediction for Scalable Spreadsheet Table Understanding: From Cell Types to Table Ranges (Extended Version) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16050 - On Stopping Rules and Spatial Adaptation for CART Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15649 - Convex Optimization with Nested Evolving Feasible Sets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07386 - Self-Supervised Noise2Noise-Enhanced Denoising for Continuous-Scan Air-Plasma THz Spectroscopy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16454 - Convolution Smoothed Quantile Regression for XGBoost Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15290 - Contraction-Aware Reinforcement Learning for Nonlinear Control with Statistical Robustness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.15700 - DumpsterCluster: From Dumpster Diving to Serving LLaMA-70B on $60 GPUs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14614 - Ask to Be Sure: Informative Interactions for Confident Multi-Turn LLM Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15949 - EMS Coreset: An Efficient Expectation-Maximization Algorithm for Sinkhorn Coreset Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16101 - Evaluating the impact of adversarial traffic patterns on vanet communication using veins simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14583 - PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16419 - Feature-Aware (Hyper)graph Generation via Next-Scale Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.01467 - A Unified Mamba--MoE Surrogate for Closed-Loop Simulation and Measurement-Window Forecasting of Inverter Transients Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15051 - PWLR: Pairwise Witness Local Rejection for Boundary-Aware Out-of-Distribution Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15802 - Evaluating the trustworthiness of the Fr\'echet Inception Distance with stochastic embedding representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21979 - Learning to Bid with Unknown Private Values in Budget-Constrained First-Price Auctions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09448 - Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15224 - Machine Learning Approaches to Decoding Topological Quantum Codes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15760 - Efficient Coreset Selection via K-Nearest Neighbor Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16270 - Architecture-Dependent Causal Transfer of Activation States Across Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16347 - Geometry of Forgetting: Representation Flux in Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15854 - Do LLMs Know What to Ask and When? Evaluating Multi-Turn Information Seeking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14808 - Would this change your answer? Evaluating Explanations of LLM Behavior In The Wild with Counterfactual Experiments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16747 - Layers Matter: Why Continual Learning Regularization Should Be Layer-Adaptive Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15901 - Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2303.07152 - Operator-Theoretic Generalization Bounds for Multitask Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15982 - Wolff-Parkinson-White Detection at 471:1 Class Imbalance: A Leakage-Controlled Study of the Data Bottleneck Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14633 - Automating Learner Assessment: Benchmarking Machine Learning and Deep Learning Models for EEG-Based Familiarity Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16541 - Paired Exact-Reset Evaluation of a Prediction-Derived Medium-to-Full World-Model Cascade Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14650 - Hybrid quantum recurrent neural network for remaining useful life prediction of turbofan engines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.20823 - Generalized Linear Bandits with Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15848 - Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocols Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.19894 - Anatomy of a Quantized Agent: VRAM Stability and Forecasting in Code-Synthesis Agentic Workloads Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15117 - Belayer: Efficient Fault Tolerance for LLM Agentic RL Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14635 - Quantum Models with Multi-Stage Training for Compositional Concept Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15601 - GATTA: Graph Active Learning with Test-Time Augmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15084 - Adding Voice Cloning to Text-to-Audio-Video Models with a Single Zero-Initialised Layer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15690 - Identifying parameter couplings and uncertainties of mixed-noise stochastic systems via full-covariance Gaussian mixture network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15198 - Local Gains and Fixed-Assignment Set Losses in Shared Set Decoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14717 - Offline Reinforcement Learning for Hemodynamic Management of Sepsis in the ICU: a MIMIC-IV Study with Dual Off-Policy Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16482 - LORA-CRAFT: Cross-layer Rank Adaptation via Frozen Tucker Decomposition of Pre-trained Attention Weights Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17510 - A Novel Fourier Feature Network for Solving Partial Differential Equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14733 - MINT: Min-Selection Preference Distillation for Balanced Multi-Objective Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14828 - BRAID: Learning Equilibrium Maps in Interdependent Security Games via Weight-Tied Iterative Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14856 - From Monte Carlo to neural networks approximations of boundary value problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2209.01432 - AsyTO: Asymmetric Temporal Operator for Parameter-Efficient Multivariate Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16098 - Thinking Outside the (Gray) Box: A Context-Based Score for Assessing Value and Originality in Neural Text Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.13207 - Online Convex Optimization with Dueling Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15050 - Experimentally Extending Quantum Kernel Learning to Quantum Data by NMR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.09557 - Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02909 - The canonical facets of multi-separator polytopes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16861 - Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.14345 - Hoeffding adaptive splitting trees for data stream classification with concept drift and ensemble learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16659 - Improved Regret Analysis for Parallel Gaussian Process Bandit Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16492 - POI Recommendation with LLM-Augmented Multi-Graph Learning and Contrastive Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16407 - Iterative Refinement Diffusion for Super-Resolved Data Assimilation of Multiscale Physical Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14744 - A Low-Cost IoT Device for Environmental Monitoring and Embedded Solar Forecasting with On-Device Incremental Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14698 - SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04419 - LLMs Can Predict Failure Risk, But Struggle to Predict Which Collaboration Protocol Pays Off: Cost-Aware Protocol Routing Across Reasoning Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14927 - Toward Optimal Second-Order Path-Length Guarantee for Adversarial Multi-Armed Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15996 - What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14819 - $S^3$: A Smooth Simulation Surrogate for Optimizing Discrete Abstractions of Dynamical Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15920 - Calibrated Trust, Not Sharper Prediction: An Empirical Test of Uncertainty Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14617 - Inferential Evaluation of Surrogate-Derived Models under Covariate Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15783 - Beyond Field Accuracy: Two-Axis Diagnosis of Inverse-PINN Parameter Error Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15373 - A Reproducibility Study of Partial Residual Ablations in Pre-LN Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14689 - PLeDO: Pain Level Detection for Osteoarthritis from EMR Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15719 - Projection-based multifidelity linear regression for data-scarce applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.08517 - MDP Planning as Policy Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17375 - Does 1/2-Tsallis-INF Also Work Well for Best-Arm Identification? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15365 - MAPLE: MoE Adaptive Plug-and-play Layer-wise Expert allocation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15299 - Unraveling the Size Determination Mechanism of Nanocrystal Synthesis via Interpretable Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14734 - Earth Observation Foundation Models for Terrestrial Ecohydrology: From Representation Learning to Process Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15282 - Learning reshapes power-law anisotropy in internal representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15239 - BDIP-Net: Dual-Interaction Graph Learning for Property Prediction of Bilayer Materials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14640 - Continuous Quantum Feedback Control via Kraus-Parameterized Belief Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15715 - Asymptotics-guided learning and symbolic regression for dispersive resonances Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16152 - Large Language Models as Implicit Sociological Models: Reconstructing Voting Behaviour from Sociodemographic Profiles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15871 - T-LLM Compiler: Trusted LLM-based Code Optimization and Verification Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14953 - Variational Outlier-Robust Gaussian Process Regression with Generative Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16606 - Randomly initialized autoencoders: fixed points and edge-of-chaos Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14638 - SchurQuant: Groupwise Discrete Optimization for Layer-Wise LLM Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15567 - Explainable Heterogeneous Anomaly Detection in Financial Networks via Adaptive Expert Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.17088 - When Uncertainty Isn't Enough: An Empirical Study of Self-Correction in Code Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14659 - High-Dimensional Nonparametric Change-Point Detection via Low-Rank Degree-Three Density Projection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15466 - A Probabilistic Circuit-Induced Pseudo-Metric for Out-of-Distribution Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09117 - The Ethical Decision Head: Operationalizing Normative Ethics in Autonomous Vehicles via Reinforcement Learning from Human Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16710 - CoM$^3$eT: A foundation model for medical image analysis through federated, multidimensional context integration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16268 - FedImp: Enhancing Federated Learning Convergence with Impurity-Based Weighting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14654 - RagGAD: Rationale-Aware Conditional Gaussian Mixture Normalizing Flow for Unsupervised Graph Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16018 - Do Geometry-Aware Positional Encodings Help Transformers in Spatial Imperfect-Information Games? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14982 - PandasCorpus: A Resource of Real-World Pandas Workflows and Usage Patterns Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14742 - Prototype-Rectified Iterative Self-supervised Manifold Denoising under Severe Acoustic Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15037 - Deep Analog: Open-Set Film Emulation with Reference-Conditioned 3D LUTs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14702 - When Does the Best Sampling Temperature Rise with the Budget? Sufficient Conditions for Pass@k Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14665 - Optimal Watermark Localization in Mixed-Source Large Language Model Texts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14906 - Does the Heart Show Your Pain? Tackling the X-ITE Pain Challenge with Self-Supervised ECG Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14662 - Q-based Variational Inverse Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16888 - Phase-Aware CNN for Real-Time 5G/6G Channel Estimation with Hardware-in-the-loop Validation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14676 - Resource-Efficient QUBO Formulation for Anchored Currency Arbitrage Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15889 - Leveraging Machine Unlearning for Cost-Efficient Preference Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.06659 - Wiring Beats Blending: What Transfers Between Transformer Sizes -- and What Doesn't Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02829 - Deep learning-based computed tomography (CT) derived body composition classifier for colorectal cancer patients Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15712 - Sequential Batch Learning in Finite-Action Linear Contextual Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2004.06321 - ETHOS: Towards a Modular Ethics Framework for Clinical Multi-Agent Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15424 - Robust Privacy: Inference-Stage Privacy through Certified Robustness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17360 - Helios 2.0: A Robust, Ultra-Low Power Gesture Recognition System Optimised for Event-Sensor based Wearables Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.07825 - No Task Fails Every Time: Why One-Shot Audits Are Structurally Blind to Agent Damage Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15286 - Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09761 - When do machine-learned exchange-correlation improvements inherit into density-functional tight binding? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14875 - A 2-Block Architecture for Real-Time EEG Gait Decoding: A Pilot Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02083 - The Physical Cutoff Does Not Restore Homogenization: Phase-Dependent Burning in the Strain G-Equation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15337 - pico-type: A 1.5M-Parameter Byte-Level Multi-Head Content Classifier Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14658 - Representation Is Not Enough: Body-Localized Thermal Evidence for Contactless Stress and Craving Sensing in Opioid Use Disorder Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16087 - Iso-Riemannian Optimization on Learned Data Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.21033 - Generative Learning of Separatrices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14743 - JAPE: Joint Anomaly Prediction and Intrinsic Explanation in Multivariate Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11801 - Metaplasticity as adaptive gradient preconditioning for incremental learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14634 - Explainability Boosted Anomaly Detection Framework for O-RAN based NextG Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14826 - Sparse Prototype Code Underlies Classification and Prediction Across Modalities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15632 - Non-Crossing Deep Quantile Regression for Distributional Survival Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16864 - RetroMPA: A Molecular Property-Aware Auxiliary Framework for Enhancing Retrosynthesis Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16111 - RT-Lynx: Putting GEMM Sparsity in the Right Place for Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26632 - Forward Pass Domain Adaptation (Without Cross-Layer Backpropagation) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14563 - Crystal-structure design by agentic AI in a language of motifs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15900 - Developing an Offshore Machine Learning Surface Layer Scheme Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14935 - Quantum Large Language Models via Tensor Network Disentanglers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.17397 - Random Quadratic Form with random forcing: Metastable synchronization by noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16664 - AutoSR: Automatic Symbolic Regression by Searching Research States Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16876 - Decentralized Federated Learning by Partial Message Exchange Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.01730 - Second-Moment Memory in Coordinatewise Adam Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15824 - Turning spectra into images improves plant trait retrieval with 2D-CNNs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16661 - Improving the matrix multiplication exponent with modern optimization and AlphaEvolve Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16884 - EMASAM: a Computationally Efficient Sharpness-Aware Minimization via EMA-Guided Perturbations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15105 - Discovering High-Quality Chess Puzzles with Offline Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14851 - Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15869 - PL-Guard: Probabilistic Logic Reasoning for LLM Guardrails Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15673 - Disentangling Homophily and Rarity: Explaining Failure in Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14823 - When Single-Dataset Conclusions Fail: A 45-Task Study of Threshold Tuning and Resampling for Imbalanced Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16147 - Measuring the Prevalence of Policy Violating Content with ML Assisted Sampling and LLM Labeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18518 - ClawGym II: Exploring Black-Box RL on Agent Harness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16798 - Optimizing Multi-Market Participation of Battery and Electrolyser Systems Based on Field Performance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16238 - Routing Divergence Is Not Evidence of Behavioral Influence in Same-Weight MoE Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15787 - SAGA: Structure-Attended Generative Action Embedding Model that encodes Multi-Surface User Action Sequences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15429 - A Physics-Informed Hybrid Neural Operator for Transient Magnetization Prediction in Power Magnetics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02965 - ARISE: An adaptive residual-informed stability ensemble for feature selection in small-sample biomedical omics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14866 - LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14626 - Lipschitz Bandits with Arbitrary Feedback Delays Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15036 - Cross-Entropy Risk Estimation for Language Models: Inconsistency Must Be Dense, and the Holdout Method Is No Exception Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15798 - The Distributional View of Knowledge Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15215 - Every Expert Counts: ExactMoE for Memory-Efficient W4A16 Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15383 - Coverage-Maximizing Multinomial Subset Routing under Operational Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16375 - Distribution-free false-alarm calibration and chance-corrected spatial evaluation for industrial anomaly detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15090 - Large Models for Small Devices: Recent Advances and Empirical Analysis of Edge AI Deployment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15693 - Beyond Binary Priorities: Multi-Tier SLA Scheduling for Large Language Model Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16336 - Efficient Safety Alignment of Language Models via Latent Personality Traits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07918 - ReliaGate: Reliability Routing for Low-Stakes Wearable Stress Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15951 - KOALA: Koopman Operator Learning for WiFi-Based Anticipatory Hum Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15815 - Analytical Provisioning for Attention-FFN Disaggregated LLM Serving under Stochastic Workloads Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21351 - CaliBench: Are the Stochastic Dynamics of Video World Models Physically Calibrated? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16829 - Memory-Bounded Continuation of Greedy Sampling for Continual Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15277 - Last-Iterate Analyses of FTRL with the 1/2-Tsallis Entropy in Stochastic Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.22819 - Supervising the Path to Fine Scales: GalerkinFlow for Scientific-Field and Image Super-Resolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16546 - How Many Samples Are Needed to Determine Causal Direction? Sharp Minimax Bounds for Bivariate LiNGAM Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15840 - Beyond Boundary Noise: Aggregated Aleatoric Uncertainty Fails to Capture Presence Ambiguity in 3D Lung Nodule Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14766 - In-Context Learning to Assess Built Environment Impacts on Perceived Neighborhood Walkability Among Mobility-impaired Older Adults Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14663 - Learning Optimal Dynamic Matching via Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28925 - SoftModel: A Neural Model That Grows Its Own Topology -- Governed Structural Growth for Continual In-Service Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16409 - Longitudinal and Graph-Augmented Prediction of Adolescent Substance Use Onset in the ABCD Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14578 - ShadowNet for Data-Centric Quantum System Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2308.11290 - Understanding and Stabilizing Deep Q-Learning via Controlled Bootstrapping and Regulated Value Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16182 - Certifying Compressed Language Models: An Audit and a Statistical Toolkit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15046 - Le Critique: Privileged Value Functions for LLM Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16739 - Multilook Coherent Imaging: Theoretical Guarantees and Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.23594 - Invariant Pretraining for Robust Code Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15412 - TokenSTFormer: A Tokenized Spatial-temporal Attention Model for Holistic Motion Analysis in Adolescent Idiopathic Scoliosis Screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16122 - SAUL: Sharpness-Aware Augmented-Lagrangian Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16249 - Decision-Driven Regularization: A Blended Model for Learning and Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15124 - A Privacy Study of Sparse Collaborative Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16236 - Breaking the Compression Barrier: Cross-Architecture Compression Boundary Learning via Reverse Regrowth Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16010 - Learning Stock Trading Policies via Barycenter-Based Adversarial Inverse Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15770 - Privacy-Preserving Dataset Curation for Kuala Lumpur Urban Traffic: Grounded Vision-Language Detection with Spatial Vehicle-Context Filtering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14724 - Prompting is not enough: supervised baselines and leakage control for measuring shared decision-making with LLMs in pediatric encounters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14792 - Eigenanalysis framework for autoregressive neural emulators of multi-scale chaotic dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16084 - A Vision Transformer for ECG-Based Detection of Left Ventricular Systolic Dysfunction Across Multiple Clinical Sites Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14723 - FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.03096 - GraniKV: Asymmetric Granularity KV-Cache Paging for Multi-Agent Systems with Long Shared Prefix Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15584 - Deploying Frontier Agentic Technology in MOOSEnger, a Multiphysics-Capable AI Assistant Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15881 - Retrofit: Continual Learning with Controlled Forgetting for Binary Security Detection and Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.11439 - A Banach-Space Theory of Markovian Halpern Iteration for Non-Expansive Maps Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15966 - SAPE: Sandwich Adapters for Parameter Efficiency in Large Language Model Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15360 - Rethinking Reverse KL as Adaptive Entropy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14685 - OceanDepths: A Global Dataset of Paired Subsurface and Surface Ocean Observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16373 - Geometry Is Not Robustness: A Trajectory-Level Study of PGD Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14594 - QuantumPhaseNet: A Gauge-Covariant Geometric and Quantum-Spectral Theory of Semantic Concept Hierarchies with Prototype Validation of a Classical Quantum-Inspired Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15820 - Maintaining IoT Device Identification under Concept Drift via Budget-Aware Traffic Labeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15465 - Feasible and Novel Synthetic Population Generation with Tabular and Sequential Travel Attributes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15867 - Guaranteed Adaptive Modality Acquisition: When the Policy Chooses Its Own Calibration Group Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15520 - MoE-Enhanced Explainable Deep Manifold Transformation for Complex Data Embedding and Visualization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.19504 - In Defense of OCTA: The Reconstruction-Utility Gap in OCT-to-OCTA Synthesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15626 - Time-Aware Validation of Machine Learning Fuel Consumption Models: Evidence from 1\,Hz Operational Data, CCGS \textit{Sir Wilfrid Laurier} Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16833 - SCALE: State-Calibrated Latent Embeddings for JEPA Planning in the Right Geometry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16287 - Auxiliary uncertainty signals for LLM-assisted systematic review screening: a benchmark across eight Cohen drug-class reviews Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14551 - Unifying Graph Neural Networks Through a Common Layer Equation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16097 - Joint MDPs and Reinforcement Learning in Coupled-Dynamics Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.06946 - AMPLIFAI: A Multiphase CT Dataset for Benchmarking Clinical Reasoning in LI-RADS Assessment of Liver Lesions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14778 - FirstDiff: One-Step Diffusion-Based Anomaly Detection for Multivariate Time Series via Initial Noise Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15727 - Multi-Feature Riemannian Hypergraph for Online Test-Time Adaptation of Motor Imagery Brain-Computer Interface Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16134 - Scaling Laws for Dynamic Mini-Batch SGD in Sketched Linear Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24316 - Global Simulation-Guided Dynamic Operator Scheduling for Efficient Multi-Tenant Model Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15762 - P2E-VQ: ECG-linked representation augmentation for PPG via discrete patch retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14656 - Mitigating Rubric Interference in LLM Judges via On-Policy Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14684 - Towards Reasonable Molecular Structure Elucidation from Infrared Spectroscopy with Chemical Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16082 - RigidBench: Evaluating Rigid-Body Physics in Video Generation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15555 - Multi-Bin Batching for Increasing LLM Inference Throughput Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.04504 - Decorrelation Is Not Complementarity: Skill, Not Lineage, Governs Trusted-Monitor Ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16190 - Sum-of-Squares Degree Barriers for the Reweighted-Hinge Method in Robust Halfspace Learning: A Christoffel-Function Characterization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17215 - Pushing the Limits of High-Resolution Weather Forecasting through Data Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14652 - PhyxMamba: Chaotic System Reconstruction from Short Context Observations with Generative State-Space Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.23863 - A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14824 - Beat the Counter First: A Baseline for Temporal-Graph Anomaly Detectors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15965 - ROC-n-reroll: How verifier imperfection affects test-time scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.12399 - Spectral Gaps of Hit-and-Run and Coordinate Hit-and-Run Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16878 - Near-Optimal Sample Complexity Bounds for Constrained Average-Reward MDPs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.16586 - Model Inversion Attacks: A Survey of Approaches and Countermeasures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.10023 - Quantifying Depth Sufficiency in Residual Neural Networks: A First-Order Criterion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14664 - Which Question Is Your Attention Metric Answering? Attention Rows as Compositional Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14712 - Zero-Shot Adaptation of Medical Vision Foundation Models for High-Frequency Micro-Ultrasound Prostate Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14796 - Explaining Reinforcement Learning Decisions in Self-adaptive Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14620 - Prediction Inference of Time Series with Standard ReLU Deep Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15362 - Spinning Conformal Correlators from Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15001 - Enhancing Differentially Private Linear Regression via Public Second-Moment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.18037 - QSMP: finding representative time series subsequences through Quick Shift+Matrix Profile Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15492 - Information Geometry of Message Passing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15922 - Workspace Topology as an Attack Vector in Agentic Coding Assistants Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14876 - A Unified Geometric Framework for Developmental Analysis of Spatial Transcriptomic Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15306 - MiNO: Cotangent-bundle propagator learning for PDEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15187 - On Stopping Times of Power-one Sequential Tests: Tight Lower and Upper Bounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.19952 - Population Structure Analysis of an Inbred Population using Quantitative Shape Phenotyping from Stereo Retinal Photographs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15471 - Domain-Specific Text Embedding Models for Entity Resolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16161 - Task-Anchored Representation Shaping for Pre-Trained Model-Based Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16345 - WANDR: A Benchmark for Wide and Deep Research Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14747 - Fractional Optimizers Meet Fractal Activation Functions: An Empirical Study of Multi-Scale Optimization in Neural Network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14636 - Convolution-Free Holistic Multivariance Decomposition Layer for Efficient Hyperspectral Image Classification Tensor Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16241 - Beyond Peak Backlog: Conditional Energy and Temporal Geometry in Capacity-Constrained Delayed Bandit Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16216 - SCPP: A Unified Python Library for Soft Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19620 - Domain-Agnostic Neural Topic Modeling with Contextual Token-Level Semantic Graph Representation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16269 - Neurai-VN Benchmark: Standardized Machine Learning Models for Multimodal Digital Phenotyping in Mental Health Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.25232 - RadioVIL: Anomaly-Aware Diffusion Models for Radio Map Inpainting and Zero-Shot Vehicle Localization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16167 - LaGSplat: Inferring Physics-Governed Interactive Simulation from Monocular Video Using Latent Lagrangian Gaussian Splatting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16324 - Probabilistic Circuits as Reasoning Machines in Artificial Intelligence (Part I) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16565 - Probability-Preserving Transformer for the Time-Dependent Schr\"odinger Equation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15112 - Coded Hankel Polynomial Chaos: Spectral Identification of Dominant Polynomial-Chaos Modes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16126 - Global Convergence of DGM and PINN Algorithms for Solving Nonlinear PDEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24726 - BERTopic-Virality Prioritisation: A Scalable Framework for Thematic and Comparative Analysis of COVID-19 and Monkeypox Misinformation on Twitter Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15691 - iFuzz-Meta: An Interpretable Fuzzy Learning Framework Bridging Top-Down and Bottom-Up Knowledge Integration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14646 - Shape Operator PCA: Curvature-Aware Projections for Geometric Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15313 - Speculative Rollback Correction for Quality-Diverse Web Agent Imitation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12485 - BrainLinear: A Linear Model for Brain Network Analysis in Sparse Tangent Subspaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15266 - Closing the Loop: A Control-Theoretic Framework for Provably Stable Time Series Forecasting with LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.12756 - FETERS: Few-Shot Early Time-Series Classification via Effective Ratio Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16385 - Bringing Generative Learning to Representation Learning: Self-Supervised Transfer Learning as Distribution Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.14424 - Hardware-in-the-Loop Phase-Aware CNN for Real-Time 5G Channel Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14709 - ConfRetro: a 3D-aware template-free method for enhancing retrosynthesis via molecular conformer information Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.12434 - Is Grokking a Loss of Normal Hyperbolicity of the Interpolation Manifold? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14803 - PureTD: Reinforcement Learning for Backgammon Money Games with No Evaluation-time Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15146 - Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.14894 - Offline Ambient-Controlled Latent Diffusion: Architecture, Telemetry, and On-Device Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14677 - SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.25459 - The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level Energy Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27599 - Measuring Structured Predictability in Neural Training Dynamics: A Cross-Regime Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15483 - Mint-Agent: Introducing Finance-Native Agentic Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16386 - 6G Native AI and Channel Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14591 - Graph Machine Learning: An Opportunity for Power Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16494 - Adaptive Heterogeneous Compression for Resource-Efficient Federated Knowledge Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15660 - DirMixE: Harnessing Test Agnostic Long-tail Recognition with Hierarchical Label Variations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.07780 - When to Communicate: Belief Distributions and KL Divergence for Principled Gating in Multi-Agent RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14559 - Fast Test-Time Refinement for Robust Learned Image Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15113 - Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14706 - GOD: Enhancing Generalization via Deep Grafting for Sequential Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16073 - Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.18911 - Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28850 - Q-Regularized Generative Auto-Bidding: From Suboptimal Trajectories to Optimal Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.02754 - DeltaLog: Deferred Materialization of Recurrent States for Linear Attention Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15533 - DeepOHeat-v2: Self-Improving Operator Learning for Fast and Trustworthy Thermal Optimization in 3D-IC Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16080 - NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruption Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16038 - On Fibonacci Ensembles: An Alternative Approach to Ensemble Learning Inspired by the Timeless Architecture of the Golden Ratio Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.22284 - An Analytical-Prior Framework for Data-Efficient Prediction of Sound-Reduction Frequencies in Rectangular Side-Branch Helmholtz Resonators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16873 - Learning Varying Physical Therapist-Patient Interactions for Robot-mediated Upper Limb Task-Specific Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15995 - Digital Twin Degradation: Detecting Cyber Physical Attacks via Temporal Inconsistencies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16159 - Efficient Neural-Network-Based High-Resolution Radiative Transfer for CO___ Retrieval, and Application to Interferometric Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14645 - Leveraging Generative Artificial Intelligence for Causal Inference with Unstructured Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.03897 - LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10139 - Differentiable Thermodynamic Phase-Equilibria for Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.11249 - FAST-DeepONet: Factor-Augmented Branch Representations for High-Dimensional PDE Inputs in the Small-Sample Regime Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15408 - ODTlearn: A Package for Learning Optimal Decision Trees for Prediction and Prescription Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2307.15691 - Correlation Clustering with Random Partial Information Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16315 - PRO-Bid: Pareto-Prioritized Regret Optimization for Constraint-Aware Generative Auto-Bidding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08261 - CFR without Unbiasedness: Deterministic Guarantees for Persistent Public-Chance Schedules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14761 - STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14861 - Learning Discrete Riemannian Metrics for Physical Fields with Cochain-Frame Equivarianc Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14556 - Towards a theory of inference-time alignment with unknown rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15402 - Temporal Logic Guided Universal Task Representations for Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15509 - Balancing Optimality and Diversity: Human-Centered Decision Making through Generative Curation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2409.11535 - Degeneracy Counting Quantum Algorithm using Decoherence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14941 - Protein Structure Prediction: From Evolutionary Constraints to Generative Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16094 - Encoding of musical structures in hidden units of restricted Boltzmann machines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.04899 - REFLEX: Reflexive Equilibrium Fixed-point Learning for Endogenous eXchanges Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16155 - Fiber Fingerprints of Hidden Learning-State Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15976 - Learning Generalizable Reconstruction of High-Dimensional Neural Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16569 - Federated Self-Supervised Modulation Classification under Non-IID and Imbalanced Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.04927 - NeuRoute: Logit-Guided Neural Routing for Billion-Scale Vector Search with Sub-Hour Index Construction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15438 - Ring-based Spatial Transformer: Learning Non-linear Spatial Interactions between Building Distribution and Pedestrian Flow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14660 - Learning to Unlearn: Machine Unlearning via Learning the Unlearning Behaviors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16700 - CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.10496 - LLMs for Zero-Shot Threat Detection via Structured Risk Indicators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16508 - From Uniform to Learned Knots: A Study of Spline-Based Numerical Encodings for Tabular Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.05635 - ARGUS: Attention-Guided Transformers for Scalable Person Identification Using Wi-Fi Telemetry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14670 - Self-Routed Tensor Adapters for Parameter-Efficient Universal Visual Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16384 - Temporal Graph Prototype-conditioned Conformal Prediction for Fraud Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15768 - Near-Equilibrium Propagation training in nonlinear wave systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.16084 - Optimal Lower Bounds for Networked Information Aggregation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15472 - Coarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14570 - Comprehensive language-image pre-training for 3D medical image understanding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.15042 - The Null Token Knows: Reducing Message-Free Hallucination in ASR and NMT Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15940 - Functional anatomy of Pythia-Herwig differences with Kolmogorov-Arnold networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15952 - Tail-Aware Top-$k$ On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14728 - Localized TabICLv2: Scaling Tabular In-Context Learning through k-NN Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16429 - Global Federated Learning Strategies for Building Efficient Personalized Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15107 - Spectral Saliency for Machine Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15548 - LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03057 - Sequential Multimodal Evidence Optimization for Product Media Ranking in E-Commerce Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15662 - A Theoretical Framework for Statistical Evaluability of Generative Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.05324 - Multi-Granularity Sentiment Integration for LLM-Based Multimodal Sentiment Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16201 - Can Neural Networks Learn by Experimenting on Themselves? Self-Interventional Learning from Functional Consequences to Predictive Self-Knowledge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14894 - A Deep Learning Model for Spatially Clustered Data via Differentiable Cluster Assignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14968 - Unsupervised Learning of Cell Instances with Generative Routing Pyramids Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16810 - Exact Attention Sensitivity and the Geometry of Transformer Stability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18849 - IP Protection in the Era of Visual Generative AI: A Survey Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14730 - Scale-Consistent Posterior Dynamics for Diffusion Inverse Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15144 - A Tree-Structured Approach for Phishing Template and Attacker Attribution Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16158 - Beyond Effective Sample Size: Effective Number of Proposals for Adaptive Importance Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15154 - DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14644 - Training and Evaluating Ethical Reinforcement Learning Agents on Per-Episode Distributions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14642 - From Recoverability to Functional Use: Auditing Temporal Reports in Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10433 - Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14648 - Discrete Diffusion Language Models Are Training-Free Multi-Label Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14649 - zLend: A Dual-Scope Cash-Flow Reconstruction Framework for On-Chain Credit Underwriting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16856 - The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16630 - Pointer Networks with Q-Learning for Combinatorial Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2311.02629 - Provenance, Not Behaviour: A Serialisation Artifact in Edge-IIoTset and a Leakage-Free Benchmark for Precision-Agriculture Intrusion Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15761 - A Pre-Specified Construction-Confirmation Test of Operation-Level Causal Transfer Across Finite Isomorphic Symbolic Domains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15809 - ProteoKnight: Convolution-based Phage Virion Protein Classification and Uncertainty Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.07345 - FinFraudBench: A Heterogeneous Graph Benchmark for Financial Fraud Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15177 - Diffusion-model approach to flavor models: A case study for $S_4^\prime$ modular flavor model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.00944 - Self-Supervised Auxiliary Task Discovery for Stable Reinforcement Learning in Stock Trading Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15841 - UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16696 - Can Attribution Predict Risk? From Multi-View Attribution to Planning Risk Signals in End-to-End Autonomous Driving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06264 - Reference-free logged energy-oracle recovery for neural approximations of symmetric coercive variational problems: conforming Riesz reconstruction and archive-level selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16473 - Solvable Sokoban Without a Solver via Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15958 - Rotation-Invariant Multi-IMU Activity Recognition under Independent Per-Location Orientation Shifts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15621 - L3Cube-IndicQuest v2: A Large-Scale Multilingual Benchmark for Evaluating Factual Knowledge of Large Language Models Across Indic Languages Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15535 - UniFed-VLM: Federated Instruction Tuning for Vision-Language Models with Multiple Heterogeneity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15516 - Detecting Money Laundering in Rwandan Mobile Money: A Machine Learning Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15447 - Hierarchical Copula-Gumbel-Top-K Routing: Two-Sided Dependence Control for Frozen Mixture-of-Experts at Fixed Per-Token Routing Laws Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28670 - Spectral Rank Certification for Foundation Model Adapters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15351 - SkillComposer: Learning Reusable Skills for Natural-Language Robot Programming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14944 - When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15639 - Knowing When to Defer: Selective Prediction for Responsible Knowledge Tracing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.21514 - M-LINKX: Multiview Graph Learning for Brain Cognitive Disease Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14847 - Time-Correlated Video Bridge Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.12453 - FDA-Opt: Federated Fine-Tuning via Dynamic Update Schedules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.04535 - Look Before You Lift: Visual and Quantitative Diagnostics for Topological Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15388 - Dynamic Pricing and Advertising with Demand Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2304.14385 - AdROD: HyperNetwork-based Adversarially Robust Object Detection for Autonomous Driving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16031 - Data-Driven Reconstruction of Spatially Resolved Electron and Ion Energy Distributions from Macroscopic Plasma Quantities with Deep Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16519 - MIRROR: Multimodal Intelligent Radiology Reasoning and Observation Reporter Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16709 - A Counterexample to the Tang Zhang Schatten Norm Conjecture and Sharp Positive Results Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15558 - Predicting, Evaluating, and Explaining Top Misinformation Spreaders via Archetypal User Behavior Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16323 - One Score, Two Decisions: Selective Prediction on the Rare-Disease Tail Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14683 - Cross-Modal Ultrasound-MRI Learning for Fetal Brain Ventricular Volumetry and Abnormality Screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14763 - NPU Offloading of a Frozen Visual Encoder for Robot Policy Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15002 - Whose Gold? Annotator-Pool Disagreement Is Large at the Item Level, and Hidden by Small Leaderboards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15980 - Replacing Tunable Parameters in Weather and Climate Models with State-Dependent Functions using Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.04268 - Retrieval-guided Twin Fusion with Similarity-aware Contrast for Molecule-Text Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16005 - CrevasseSeg: A Label-Efficient UAV Crevasse Segmentation Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15790 - TRACE-CASH: Trial-History-Conditioned Reinforcement Learning for Adaptive Configuration Exploration in Time-Series CASH Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16410 - TransfHAR: Self-Supervised Wrist Representations for On-Demand Activity Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15861 - LLM-based Framework for Generating and Verifying Parallel DEVS Statecharts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14956 - Do Uncertainty Signals Help? A Systematic Study of Uncertainty-Aware Decoding with Rollback Mechanisms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14653 - Diagnosing and Mitigating Perception-Decision Misalignment in Omni-LLMs via Modality Subspace Activation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14655 - Transfer Learning of Keystroke Dynamics for Cross-Device User Authentication Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16334 - Conditional Evaluation of Language Models with Cheap Auxiliary Signals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16210 - Doubly robust nearest neighbors in factor models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2211.14297 - Represent, Then Generate: Multimodal-Conditioned Time-Series Generation under Irregular Missingness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12592 - Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15669 - FedPA-LoRA: Product-Aligned Framework for Mitigating Aggregation and Initialization Errors in Heterogeneous Federated LoRA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15381 - Valid Per-Field Selective Risk Control for Document Extraction: Three Failure Modes, a Validity Ladder, and When Conditioning Pays Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14639 - PIKFNO: An Interpretable Neural Operator Based on Physics Informed Kernel Function Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14619 - Beyond $L_2$: Generalizing Abductive Latent Explanations to Diverse Prototype-Based Architectures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16773 - Koopman early warning signals for bifurcation and rate-induced tipping Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14716 - Advancing Open and Reproducible Relational Learning: RelArena-$\alpha$, TabPFN-Rel and RPI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16319 - PERO: Efficient Robust Post-Training Foundation Models for Encrypted Traffic Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15504 ## Community - Mojo🔥 is now open source Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Aug/18/mojo-is-now-open-source/