TILens Daily Edition 2026-09-17 Filters: topic=ai-research, github=hidden Stats: 646 articles, 8 sources, 638 research papers Top topics: AI, AI Research, Information Retrieval ## News - True Positive Weekly #178 Source: true-positive-weekly Topic: AI (+AI Research) URL: https://aiweekly.substack.com/p/true-positive-weekly-177-f7f - OpenAI Reveals Six AI Safety Failures—and a Chance to Learn From Them Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/openai-six-ai-safety-failures-misalignment-reports/ - Mustafa Suleyman Has a Point About What Anthropic Is Teaching Claude Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/mustafa-suleyman-anthropic-claude-model-welfare/ - When AI Predicts Better Than People, Who Sets the Rules? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/when-ai-predicts-better-than-people-who-sets-the-rules/ - 🙀 OpenAI discloses MORE “concerning” AGENT behavior Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/openai-discloses-more-concerning-agent-behavior/ - Self-Improving AI Starts With Human Know-How Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/self-improving-ai-starts-with-human-know-how/ - Everything That Happened in AI Today (Wednesday, September 16, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-wednesday-september-16-2026/ - Would You Let AI Plan Your Workweek? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/would-you-let-ai-plan-your-workweek/ ## Research - The future of practice: Enabling teachers to create learning interactives with generative UI Source: google-research-blog Topic: AI Labs (+AI, AI Research) URL: https://research.google/blog/the-future-of-practice-enabling-teachers-to-create-learning-interactives-with-generative-ui/ - Building a Data Lakehouse with DuckDB and DuckLake Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/building-a-data-lakehouse-with-duckdb-and-ducklake/ - How I Built a Multi-Agent System for Interrupted Time Series Analysis (ITSA) Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-i-built-a-multi-agent-system-for-interrupted-time-series-analysis-itsa/ - Why You Think Like a Bayesian but Were Taught Like a Frequentist Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/why-you-think-like-a-bayesian-but-were-taught-like-a-frequentist/ - When Does Graph RAG Actually Add Value? A Hands-On Experiment Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/when-does-graph-rag-actually-add-value-a-hands-on-experiment/ - AeroWeaver: An Embodied-Agent Harness for Weaving Aerial Skills into Distributed, Adaptive Swarm Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18520 - Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19190 - FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03852 - Missing Bridges: Composition-Aware Active Imitation Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18004 - Collaborative Memory for Multi-Agent VLM Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17921 - Proprioception-Anchored Cross-Modal Pretraining for Zero-Shot Sim-to-Real Contact-Rich Assembly Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07534 - Re2A: Situated Conversational Recommendation via Rubric-based Preference Reasoning and Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18249 - Whom Do AI Agents Work For? Role Assignment Induces Sponsorship Bias in LLM Recommenders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17989 - WFM: Wiki Foundation Model for Complex Agentic Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18182 - VoiceTrace: A Benchmark and Retrieval Framework for Who-Said-What Speech Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18521 - Remembering Solomon Marcus Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18224 - Anchoring What Matters: A Dual-Level Learning Framework for Visually-Grounded Multimodal Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18057 - ERPBench: A State-Grounded Evaluation Paradigm for Computer-Use Agents in Enterprise Software Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17885 - An Empirical Evaluation of Cost-Efficient Large Language Models on Algorithmic Programming Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18052 - Securing quantum error correction against misleading advice from AI agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19090 - First Token Matters: Understanding Safety Collapse in Large Reasoning Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18471 - AI Persuasion as a Threat to Human Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14796 - The Internal Anatomy of Strategic Choice in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07478 - Why LLM Agents Collapse Without Oversight: The Enforcement Gap as the Mechanism Behind Emergence World Failures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15293 - Ultralytics YOLO Evolution: An Overview of YOLO27, YOLO26, YOLO11, YOLOv8, and YOLOv5 Object Detectors for Computer Vision and Pattern Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.09653 - BENCHCOMPASS: From Scores to Signals for Training and Harness Decisions in Payment-Domain LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18270 - GenStream: Semantic Streaming Framework for Generative Reconstruction of Human-centric Media Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18634 - Look Less, Hear Better: Jointly Rewarded GRPO for Streaming ASR Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18333 - Clueing up LLMs with Tool-Augmented Deductive Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18736 - CompArt: Operationalizing Aesthetic Alignment in Text-to-Image Generation via Principles of Art Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.12018 - CALOS: Control-Affine Lyapunov On-manifold Safety Layer for Safe Deep Reinforcement Learning for Quadrotors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17758 - AI and Human Approaches to Mathematical Problem Solving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17779 - Imitation Learning for Autonomous Driving in CARLA Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17757 - CPR: Combining global composing, local performing and full-sequence refining in piano rendering with continuous autoregressive modelling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18216 - A Mathematical Theory of Pragmatic Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10986 - Multitask Reinforcement Learning for Assisting Choice Model Specification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18441 - FrogNano: Training a 4B Coding Agent via Online Task Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07925 - SNOMED CT Concept Recommendation from Masked Clinical Context Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17855 - Multimodal Conditioning of Fine-Tuned Stable Diffusion XL for Controllable and Culturally Faithful Ulos Motif Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17987 - ShotFinder: Imagination-Driven Open-Domain Video Shot Retrieval via Web Search Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2601.23232 - HyQuant: Hybrid-Precision Quantization for LLM Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27875 - Compositional Policy Violations: When Step-Level Compliance Fails In Agentic AI Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18820 - FairCompressAgent: An Agentic Framework for Fairness-Aware Model Compression for FPGA Deployment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17786 - Generalist-Specialist Mixture-of-Experts for Rare Pathology Detection in Multimodal Imaging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18688 - Building Trust in Artificial Intelligence: A Necessity for Railway Applications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18278 - Ask the Tool, Don't Guess: Agent Tool Calls Hold Their Progress, and the Serving System Should Read It Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18849 - Decodability is Not Causality: Dissociating Probe Readouts from Behavioral Drivers via SAE Decomposition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18080 - After the Party: Growth, Governance, and Security Scanning in the OpenClaw Agent Skill Ecosystem Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17274 - Affora: A Design System for Agent-Friendly Interfaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19125 - Echo: Learning-based Matching Decompilation using Trusted Back Translation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18706 - Hypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18598 - A Non-Linear Neuron Based Detection of Isolated Pixels in Binary and Grayscale Images using Contrast Sensitive Receptive Fields Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18399 - Do Not Restart: Residual Completion for Stateful Agent Handoffs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13800 - GYROval: A Robust Benchmark for Cultural Value Orientation in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18384 - Lost in Perception: Isolating Perceptual and Reasoning Failures in Multimodal Physics and Geometry Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18991 - A visual large language foundational model for medical image recognition using clinician-contributed online resources Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06914 - Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04765 - Exploring the Potential of Contrastive Language-Image Pre-training for Multi-Source Remote Sensing Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03391 - Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12839 - Which LLM is Best for Translating Natural Language Goals to PDDL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18731 - EvoUndo: Recoverability-Constrained Self-Evolution for LLM Agent Harnesses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28363 - Contiguity, Not Importance: Budgeted Repair of Stale KV Caches After Document Edits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17983 - Not All Agreement Counts as Corroboration: Provenance-Conserving Multi-View Fusion for Typed Action Admission in Human-Robot Collaboration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01662 - Independence-System Realisations in Single-Source Unsplittable Flow Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17568 - Algorithmic Shortlisting in Participatory Budgeting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.06577 - LM Fight Arena: Benchmarking Large Multimodal Models via Game Competition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.08928 - From Alignment to Synthesis: Contrastive Volumetric Grounding for Text-to-CT Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.00633 - Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14708 - GrainSpeech: Less Context, More Detail for Compact Speech Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18856 - Exploratory Responsiveness and Adaptive Rigidity under AI-Assisted Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10086 - Measuring AI Leadership: Development and Validation of a Multidimensional Measure for AI-Native Organizations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17965 - One Color Preprocessing Improves DSATUR Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17633 - Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.16129 - Automated Dental Caries Segmentation in Panoramic Radiographs Using Dual-Stage Deep Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18952 - Diff-SPORT: Diffusion-based Sensor Placement Optimization and Reconstruction of Turbulent flows in urban environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.00214 - Governing Agentic AI in FinTech Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11344 - Making AI-Assisted Claims Independently Challengeable: Publication Authority and a Protocol for Falsifiable Publication Records Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17631 - OBC-Prune: Outcome-Based Calibration for Large Reasoning Model Pruning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17890 - Latency-Tolerant Cloud-Edge Collaborative Vision-Language-Action Models via Emergent Representational Specialization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00569 - An Agentic Framework for Neuro-Symbolic Programming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.00743 - Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01232 - Iris: Climbing to the Search Frontier Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.04304 - CapMem: A Benchmark for Caption-Based Episodic Memory in Egocentric Video Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17688 - CSWAM: Better Causal Semantic Representations for Out-of-Distribution Generalization in World Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18462 - Version- and Scope-Aware Question Answering over Normative Documents: A Deployed System and an End-to-End Evaluation at Production Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18769 - Human Resilience in the AI Era -- What Machines Can't Replace Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.25218 - Memory Has Geometry: Non-Uniform Geometric Memory for Long-Horizon Personalized AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17969 - RideWay: Benchmarking Efficient Task Completion for Tool-Using Language Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17985 - Ranking Infrared-Visible Fusion the Way Humans Do: A Learned Pairwise Preference Measure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01301 - Symbolic Temporal Supervision of LLM Agents Using Contracts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18128 - EDCT-Bench: Uncovering Faithfulness Gaps in VLMs via Explanation-Driven Counterfactual Testing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17953 - REPAIR: Resolving Long-Tail Confusion in Scientific Retrievers via Fact-Verified Iterative Refinement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18262 - Taming the Agentic RAN: Stability-Guaranteed Arbitration of Autonomous AI Agents in O-RAN Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18857 - Lexara-RF: Reference-Free Metrics for Evaluating Conversational Visual Analytics Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17842 - Flag Game: A Toy Model for Mechanistic Swarm Interpretability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19124 - PentestChain: A Cost-Aware, MCP-Orchestrated Framework for Automated Penetration Testing with Free-Tier LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18120 - Language-Guided Terrain-Adaptive Neural MPC for Autonomous Traversal of Articulated Tracked Robots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13083 - Physics-Constrained Digital Twins for Sensor Integrity in Urban Pedestrian Flow: Detecting Stealthy False Data Injection with Conformal Guarantees Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17635 - Recursive Reasoning or Statistical Extrapolation? In-Context Learning in Multi-Agent Interdependent Decision-Making Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18591 - CapMap-MS-TTA: 3rd Place Solution for the MUMU Track of the 8th LSVOS Challenge at ECCV 2026 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18206 - Information Set Emulation: Causal Certificates for AI Derived EHR Features Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17777 - Evolutionary Ensemble Search: Council-Guided Program Evolution with Persistent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17590 - The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18063 - Planning in the Backbone: DiffAdapterVLA for Native Continuous Trajectory Generation with Driving VLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15322 - AutoTuneBench: Trustworthy Measurement for Agent Auto-Tuning of LLM Serving Engines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18123 - SAGE: Governed Artifact Generation from Enterprise Guidelines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17775 - ASLEval: Measuring Privacy Exposure Displacement in LLM Agent Sessions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18864 - Teaching AI, Robotics, & Community: A Hubs-Based K-12 Education Framework for Reaching Rural Schools Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18072 - QiT: Quantum-Inspired Transformer for Visual Recognition Task Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17789 - When Is Graph Structure Worth Its Cost? The Case for Structure Pricing in Retrieval-Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18099 - The Inference Engineering Pareto Atlas: Which Optimizations Dominate the Cost, Quality, and Latency Frontier? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17863 - Detect Before You Leap: Mirage Detection in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00435 - Does AI Assistance Leave a Temporal Fingerprint? Detecting Overreliance in AI-Assisted Writing and Programming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17883 - Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.14254 - ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18805 - Safety Signals to Verify NetOps Agents with Action-Level Granularity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14422 - 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 - When to Call an LLM: A Confidence-Gated Hybrid for Cost-Effective Emotion Recognition in Conversational AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17977 - SurgRAW: Multi-Agent Workflow with Chain of Thought Reasoning for Robotic Surgical Video Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.10265 - Universal NP-Hardness of Clustering under General Utilities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.00210 - The Mirage of Calibrated Confidence: Trajectory-Independence of Verbalized Confidence in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18453 - Function Lives Where Variance Doesn't: Task-Weighted Charts of a Language Model's Computation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18989 - GVD: Governed Versioning and Deduplication for Document Repositories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17696 - Constrained PSLQ Search for Machin-like Identities Achieving Record-Low Lehmer Measures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.08307 - When AI Generates Covariates: Causal Typing and Estimand Drift in Sequential Experiments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17772 - SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08149 - Who Audits Whom, on What Substrate, with What Evidence? An Independence-Graded Audit Protocol for Agentic AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18272 - MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.24565 - little m: An AI Agent for Industrial Process Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16680 - Reflections on Trusting Trust, Revisited: Contaminating Self-Modifying AI Coding Agents with Poisoned Benchmarks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17817 - Dose-Aware Cold Diffusion with Physics Consistency for Generalizable Low-Dose CT Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18943 - HINT-Plan: Human Intention-Aware Robot Task Planning in Context-Rich Environments using Vision Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17771 - What Counts as Strategic Reasoning? A Systematic Mapping of Chess Research on Humans, Engines, and Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18286 - Designing Agentic AI Workflow Portfolios under Imperfect Selection and Compute Cost Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18126 - BadQubits: An LLM-Based Framework for Static Pre-Execution Detection of Structurally Harmful Quantum Circuits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18965 - Transcribe, Then Reason: Two-Pass Decomposition for Multimodal Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18958 - Cultural Competence in Context: A Large Language Model Passes the Turing Test in Finland Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18394 - WetRobo: A Reproducible Robot Kit for Coding Agents in Biological Laboratories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18435 - A Systematic Evaluation of the COTQ Provincial Land Cover Product: Structural Consistency, Spectral Separability, and Relative Positioning Against ESA, ESRI, and Google Products Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17731 - Autonomy in Check: Governor-Mediated Adaptive Security at the Edge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18338 - Mask 2D-3D: Adaptive Dual-Masked Autoencoder Network for Image-to-Point Cloud Registration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18088 - rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19104 - Beyond EER: Multi-Dimensional Evaluation of Information Leakage in Speaker De-Identification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18673 - Learning Multi-Humanoid Pickup and Transport via Decentralized Object-Centric Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17824 - On-the-Fly Homographies Calibration for Multi-Camera Tracking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18582 - Benchmarking LLM Judges for Voice-Agent Evaluation: Reliability, Calibration, and Human Oversight Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24314 - Predictive Assistance and the Temporal Dynamics of Exploratory Compression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10094 - Do Frontier Models Seek Safety Evidence Before Acting? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17865 - SegTME-UNI2: A Foundation Model-Based Framework for Generalisable Multiclass Cell Segmentation and LLM-Driven Tumour Microenvironment Characterisation in Histopathology Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17702 - Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19137 - Visual Compliance via Executable Safety Rule Entailment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18328 - 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 - A Study of the Reliability of Agentic AI-Generated Programs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18298 - MiST: Mid-Training LLMs for Cybersecurity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18496 - Collective Loss of Control in LLM Agent Systems: An Epidemic Account of Mutation, Contagion, and Recovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18460 - Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27141 - Geospatial Metadata Improves Discoverability by Connecting Datasets Across Scientific Disciplines Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16498 - PACT-WAM: Predicting Actions and Visual Foresight with Compact Temporal Encoding for Robot Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.15882 - Prepared Or Unprepared? Evaluating Healthcare Workforce Readiness for Clinical Adoption of Artificial Intelligence in Nigeria Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19096 - Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18357 - Faking Good and Faking Bad in LLMs: Response Distortion Across Dark Triad Personality Traits Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17534 - A Scalable Framework for Automated NER Annotation Correction in Low-Resource Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18739 - Extracting Probabilistic Knowledge from Large Language Models for Bayesian Network Parameterization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.15918 - ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19134 - Think Before You Comfort: Reflective Cognitive Alignment for Protocol-Grounded Elderly Stimulation Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17536 - Follow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor Tokens Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16847 - Knowledge-Graph Based Augmentation versus Retrieval Augmented Generation for Cultural-Related Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18317 - HALT: Hallucination Assessment via Log-probs as Time series Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02888 - TeochewBench: A Human-Reviewed Benchmark for Teochew Hanzi Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18156 - AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.23069 - Divide and Conquer: Mixture-of-Bottleneck Experts in Informative Ordinal Space for Video-based Multimodal Sentiment Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18470 - Planning or Improvisation? Stress-Testing the Poetry Planning Site on Open Models and Open Cross-Layer Transcoders Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18440 - Benchmarking Large Language Models for Biomedical Relation Extraction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19071 - Tracing individual knowledge trajectories in a changing field: the case of general relativity and gravitation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18697 - MIRAGE: How Conversation State Shapes Historical Evidence Use in Multimodal Personal Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19059 - Dependency-Aware Trajectory Refinement for Efficient Multi-Turn Agent Fine-Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18417 - Beyond frequency measures: Can contextual embeddings capture meaning change in scientific texts? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18804 - Is Trump's Vocabulary Poor? Vocabulary Richness Across Texts of Different Lenghts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17747 - Modeling the Developmental Shift in Telicity Acquisition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17996 - RankGround: Efficient High-Resolution GUI Grounding via Lightweight Reranker-Guided Crop Selection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18690 - STRETCH the Boundaries: A Unified Self-Taught Framework for Progressive LLM Evolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18642 - Myovox: Reading Speech from the Muscles of the Face Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17548 - Reporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19093 - How AI Assistants Respond to Repeated Abuse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17547 - Structured Claim-Level Discourse Representations for Dense Health Narratives Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18905 - ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18487 - SEA-LION-v4.8: A Technical Report Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18310 - MUSE: Benchmarking Large Vision-Language Models on Multi-Modal Understanding in Situated Education Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19088 - Can We Still Trace L1 Signals? Investigating the Resilience of Native Language Signals in the LLM Era Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08568 - Evolution of US Oral Political Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17755 - Beyond Accuracy: How Procedural Traces Shift the Decision Criterion of LLM Overseers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18204 - Understanding LLM Failures: A Multi-Tape Turing Machine Analysis of Systematic Errors in Language Model Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.15868 - When Cognitive Graphs Meet LLMs: BDEI Cognitive Pathways for Panic Emotional Arousal Prediction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15121 - Rollback the World, Keep the Reflection: Rollback-Induced Reflection for Long-Horizon LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18304 - From a River in Gilead to the Inference Distributions of Large Language Models: Covert Dialect Bias and Linguistic Profiling at Scale Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18068 - Enhancing knowledge tracing robustness for new question cold start in Intelligent Tutoring Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.07179 - Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14121 - Donate or Create? Comparing Data Collection Strategies for Emotion-labeled Multimodal Social Media Posts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.24427 - Register Bias in Complexity-Based Large Language Model Routing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17542 - Multi-Hop Knowledge Composition is Bound by Pretraining Exposure Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09338 - How Much is a Human Right Worth? ECtHR-NPD: A Benchmark for Predicting Non-Pecuniary Damage Awards Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18908 - Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17708 - Does Moral Reasoning Training Help or Hurt? Red-Teaming RL-Trained Ethical Agents with Persona Attacks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17552 - Accelerating Stateful Network Applications with Performance Prediction on SoC SmartNICs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.22229 - Long-Lived Characters, Local Inference: Incremental Memory Maintenance for Game NPCs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18935 - Which Demographics do LLMs Default to During Annotation? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.08820 - LangSelect: Cost-Aware Target-Language Routing for LLM Code Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18959 - Creating an Atomic User Model for Personality-Aware Large Language Model Interaction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12086 - Reading Between the Lines: Can LLMs Discover the Question Behind the Text? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19070 - SFT or RL for Tool-Calling Agents? A Controlled Study Across Data, Method, and Scale Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17848 - Using OCR Heads to Verbalize Image Semantics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18823 - Zero-Shot Cross-Lingual Recognition of Sign Language Handshapes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18772 - WordPolo: Evaluating Language Models Through Iterative Semantic Feedback Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19006 - Encoder Awakening via Adapters: Effective Domain-Adaptive Fine-tuning of Speech-LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17981 - 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 - Relationally Guided Use Case Modeling with LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18291 - Voice of Reason: Reinforcement Learning for Spoken Math Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18677 - EviGen: Predictive Evidence Scaffolding for Verifiable Clinical Rationale Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18852 - ReFigBench: Benchmarking Scientific Figure Reconstruction as Editable PowerPoint Artifacts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18844 - Schema-Key Wording as an Instruction Channel in Structured Generation under Constrained Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14862 - MudawanSn: A Gold-Standard Wolof-Arabic Parallel Corpus for Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17539 - The Limits of BPE Tokenization in Polish: Segmentation-Flexional Forms, Grammatical Anchoring, and First-Person Stability in Inflectional Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17553 - ${M}^2$Tok: Multi-head Multi-codebook Discrete Action Tokenization for Vision-Language-Action Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18259 - DyMT-ESB: Dynamic Multi-Turn Evaluation of Social Bias in User-LLM Interactions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18649 - When Audit Quality Fails to Predict Downstream Utility: A Counterfactual Study of Synthetic-Data Selectors for Low-Resource African NLP Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18960 - "If I Had to Buy Just ONE: Galaxy S26 Ultra": Auditing AI-Generated Product Recommendations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18729 - Beyond Outcomes: Dual-View Relational Learning for Efficient Agent Benchmarking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18909 - Label-Confidence-Aware Uncertainty Estimation in Natural Language Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.07255 - Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.16555 - FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18766 - Is Luke the Author of a Gospel and the Acts of the Apostles? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17762 - TurnBench: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25218 - "You are an expert annotator": Automatic Best-Worst-Scaling Annotations for Emotion Intensity Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2403.17612 - TalkMatrix: Generating Character Dialogue that is Both Consistent and Diverse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19022 - Legal LLM Hallucination Should Be Evaluated as Failure of Legal Warrant Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17546 - EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17632 - ProofVerifier: A Scalable, Diversity-Driven Framework for Natural-Language Proof Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02377 - AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.21891 - Too Good to Be Real? Diagnosing and Reducing the Gap Between AI Preference and Real User Engagement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18282 - CzechTopic: A Benchmark for Zero-Shot Topic Localization in Historical Czech Documents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03884 - DualSQL: Text-to-SQL with Multi-Agent Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18135 - A Probe Shift Is Not a Fairness Fix: The Limits of Representation Steering in Speech Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18533 - A Systematic Review of NLP for Ghanaian Languages: Datasets, Models, and a Research Roadmap Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.06818 - I code or AI code: A comparative evaluation of AI-rated scores in classroom observations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18274 - PBEBench: A Multi-Step Programming by Examples Reasoning Benchmark inspired by Historical Linguistics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.23126 - From Pixels to Pairs: A Comprehensive Benchmark of LLM-Based Key-Value Extraction in Noisy Document Settings Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17538 - Playing log(N)-Questions over Wikipedia Abstracts: Communication Efficiency Between Paired Frontier Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19113 - Emotion Experience, Expression, and Perception: Emotion Analysis on Multimodal Social Media Posts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18385 - How Do Document Parsers Break? Auditing Structural Vulnerability in Document Intelligence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19309 - NeMo Data Designer: An Extensible Framework for Multimodal Synthetic Data Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17699 - MechSparse: Mechanism-Guided Sparse PEFT Selection Is Task-Shaped Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18961 - TeleAntiFraud 2.0: A Refreshable, Profile-Grounded, and Audio-Based Benchmark for Telecom Fraud Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18748 - Mind the Style: Impact of Communication Style on Human-Chatbot Interaction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17850 - Vroom-Vroom at SHROOM-Visions: A Multi-Judge Committee for Detecting Hallucinated Spans in Vision-Language Outputs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17327 - Assessing the Effect of Cross-Domain Mapping on Creativity in Humans and Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19087 - A Taxonomy of Programming Languages for Code Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.00239 - T-SANDHI: Tone Sandhi-aware Adaptive Network with Decoupled Hybrid Injection for Low-resource Taiwanese Hokkien Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18194 - M-SQE: Multilingual Skill Quality Estimation for Enhancing Language Equality in Agentic Skill Use Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18445 - GraphEcho: Structural Redundancy and Evidence Provenance in LLM Graph Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17695 - Faithful yet Collusive: Why Chain-of-Thought Monitoring Cannot Detect Collusion in LLM Pricing Agents under Oligopolistic Competition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18346 - LocQE: Principled Domain Adaptation for Localisation Quality Estimation by Leveraging Post-Edits Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18720 - A Benchmark Suite and Ground-Truth Methodology for Formal Verification of IEC 61131-3 Ladder Diagram Programs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18994 - Large Language Models Versus Physicians in Traditional Chinese Medicine: A Real-World Clinical Case Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17544 - Made in Hungary: Comments on the performance of generative language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18284 - Notes2Skills: From Lab Notebooks to Certainty-Aware Scientific Agent Skills Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11897 - Machine Translation between English and Syriac (East Syriac Dialect) using Statistical Machine Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18529 - Parameter-Efficient Retrievers for Polish and European Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12913 - Linguistic Triggers of Gender and Racial Bias in Open-Weight LLMs Applied to Recruitment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18106 - When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25977 - DANTINOX: A Unified Framework for Multi-Paradigm Language Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17535 - English Word Sense Disambiguation in 2026: When the Labels Become the Bottleneck Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17554 - Objective vs. Search: Decomposing What Makes a Good Tokeniser Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19145 - PersonaPath: Towards Knowledge-Centric Personalized Learning Path Planning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18861 - RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12099 - Learning from Many Voices: Literary MT Using Multi-Reference Human and Synthetic Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.18707 - Entropy in Conversational AI: Structured Unpredictability as Inferrable Interiority Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19044 - Align, Integrate, and Fire: Efficient Token-Level Alignment for Zero-Shot SpeechLLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18516 - G-Mamba: Sparse Graph-Guided Mamba for Audio-Visual Speech Enhancement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18009 - Compiled Agency: Frontier General-Purpose Coding Agents Build Winning Game Players from Bare Interaction - from Flappy Bird to StarCraft II and Civilization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18996 - PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19143 - LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28077 - Zero-shot narrative detection in social messaging Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17310 - Correlation-Guided Encoder Selection for Multi-Encoder Large Audio-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18041 - Gaze as Evidence for Common Grounding: A Cross-Corpus Analysis of MapTask and MUNDEX Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18011 - Selection Is Retrieval, Abstention Is Not: On-Device Tool Routing over 70 Korean-English Actions Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.18672 - Code Consistency Preference Optimization Verification for Language Model Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19002 - Size Matters: Foundation Model for Czech HTML documents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18494 - Relation Before Entity: Deferred Commitment in Language Model Factual Recall Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17537 - HearInContext: A Benchmark for Implicit Context in Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18680 - Modelling Adjectival Modification Effects on Semantic Plausibility Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.21828 - Do Social Patterns Hold in Synthetic Data? Analyzing Cyberbullying Dynamics in LLM-Generated and Authentic Dialogues Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17549 - Time-Aligned Evolving Concept Graphs for Scientific Relation Forecasting Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.18163 - Can We Do Interpretable NLI with Graphs Based on Atomic Propositions? Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.16814 - PageRecall: Measuring Page Selection in Literature-Grounded Question Answering Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.18154 - Quanta: A Self-Contained Python Library for Hybrid Retrieval over Quantised Embeddings, Lexical Indexes, and Knowledge Graphs Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.18248 - Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.01670 - Single-Token Expected-Value Scoring for Cold-Start Candidate Ranking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.18188 - One-Step Retrieval Framework for Real-Time Sponsored Search Ads Using Hierarchical Text Representations Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.18296 - Scaling Articulated Rationales for MLLM-based Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.17639 - Understanding AI Provider Recommendations in Local Service Markets Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.18341 - An Industrial-Scale Sequential Recommender for LinkedIn Feed Ranking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2602.12354 - One Size Does Not Fit All! Dynamic Retriever and Generator Selection for RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.17709 - The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2408.07702 - Seeing Through the MiRAGE: Evaluating Multimodal Retrieval Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2510.24870 - DUPAR: Dual-Path Conversational Retrieval via Speech Retriever with Cross-Turn Evidence Caching Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.18042 - P$^3$Rec: Distilling Prior--Posterior Preference Reasoning for LLM-based Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.13993 - SURF: Subtractive Updates for Recommender Forgetting Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.18695 - How Calibration Content Shapes Attention-Based Reranking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.17764 - SEEK: Secure and Efficient Encrypted Keyword Search For Privacy-Preserving Messaging Protocols Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.18459 - Exploring LLMs and RAG for Plausible and Explainable Material Prediction of Vehicle Components Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.18437 - Abstention vs. Hallucination: Benchmarking LLM Source Attribution for Scientific Citations Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2405.02228 - On Predicting Post-Click Conversion Rate via Counterfactual Inference Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2510.04816 - From Overlooked to Explored: Recovering Item Relations via Mixture of Perspectives for Sequential Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.11846 - KITE: A Tri-Modal Transformer Integrating Text, Images, and Knowledge Graphs for Fake News Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07651 - Language-Guided Grasping under Partial Observation for Mobile Manipulation in Field Inspection and Maintenance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.07866 - Colla-Q: Toward Collaborative Experts in MoE Quantization via Minimax Precision Balancing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18131 - Hierarchical Spatio-Temporal Transformer for Coherent Emergency Department Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27106 - Exact semantic readout from compressed vector representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18047 - A Zeroth-Order Paradigm for LLM Preference Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19144 - Regional Explanations via Causal Sufficiency and Necessity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18049 - HiLNO: A Hierarchical Latent Neural Operator with Multi-Scale Supervision for PDEs on General Geometries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18419 - MINT: Multimodal Imaging-to-Speech Knowledge Transfer for Early Alzheimer's Screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23994 - Deep learning emergent spacetime from fermionic spectral functions in holography Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18566 - Benchmarking Tabular Foundation Models as Surrogates in Expensive Evolutionary Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18130 - Who Judges Matters: Measuring Family-Conditioned Preference in LLM-as-Judge Panels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17857 - Beyond Random Couplings: Contrastive Noise Alignment in Generative Flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18488 - ADAPT: Lightweight, Long-Range Machine Learning Force Fields Without Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.24115 - Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18366 - TargetSEC: Plug-and-Play In-the-Wild Speech Emotion Conversion via Arousal-Conditioned Latent Style Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07293 - When the Gradient Sees Rank: Provable Necessity, Causal Recruitment, and Composition in Trained Matrix Memories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17594 - WARD: Runtime Workload-Adaptive Vision TRansformer Framework for Dependable Edge AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17556 - TabICLv2: A better, faster, scalable, and open tabular foundation model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11139 - Learning Array Signal Topologies as Conditional Neural Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18616 - Revisiting Distributed Sign-Based Variance Reduction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18656 - Similarity Pairing with Energy Mover's Distance for Self-Supervised Pre-Training at the LHC Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17738 - Implicit Bias and Invariance: How Hopfield Networks Efficiently Learn Graph Orbits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.14338 - Symmetrizing Bregman Divergence on the Cone of Positive Definite Matrices: Which Mean to Use and Why Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28917 - Almost Sure Convergence Analysis of Stochastic Gradient Methods with Clipping and Additive Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12119 - Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19135 - 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 - What You Can't See Is Still What You Learn: A Preregistered Sixty-Society Confirmation That Evidence Masking Drives Compositional Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17637 - Interpretable Retinal Disease Prediction Using Biology-Informed Heterogeneous Graph Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.16697 - Risk-Aware World Modeling with Flow-Guided Occupancy Evolution for Selective Trajectory Planning in Automated Driving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18442 - Consensus-based optimization for closed-box adversarial attacks and a connection to evolution strategies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.24048 - GroupKV: Hierarchical KV Cache Management for Long-Context Diffusion LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17573 - Learning from Distributed Eyes: Leveraging Collaborative Perception for Automated Model Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18511 - Provable Guarantees for Spectral Structured Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18527 - Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18306 - Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18842 - Newer Is Not Fairer: Gender Stereotyping in Text-to-Image AI Across Model Generations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18007 - Revisiting the Objective of Echo Chamber Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18545 - Beyond Quadratic Loss: The Stability Phase Diagram of Adam Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18314 - Improved Regret Analysis for Parallel Gaussian Process Bandit Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16492 - Variational Quantum Transformer Architecture for Synthetic Language Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18565 - Regularized Least Squares Training of Quadratic Neural Networks with Applications to System Identification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17654 - Locating Hidden Failures Makes Long-Horizon Agents More Reliable Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17930 - Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18515 - Modular Deep Learning Mechanisms for Auditable Next-Day Wildfire Spread Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17763 - Enhancing Extubation Failure Prediction with LLM-Derived Features from Respiratory Therapy Clinical Notes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17532 - Libra: Efficient Resource Management for Agentic RL Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03077 - Token Latency Fairness: Performance Isolation for Multi-Tenant LLM Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18112 - METALICA: METAdynamics and repLICA exchange for enhanced diffusion sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17823 - Spatially Adaptive Noise Injection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18466 - Cross-Block Conditioning in Deep Boltzmann Machines for Statistical Data Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14934 - Active Learning Enables Generation of Molecules that Advance the Known Pareto Front Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.02059 - Learning Magnetic Order Classification from Large-Scale Materials Databases Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.05909 - Learning Heterogeneous Preferences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17847 - Uncertainty-Aware Continual Learning for Open-World Intent Discovery Under an evolving Label Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17866 - HPOQuest: A Rare-Disease Diagnostic Agent Using Active Phenotype Acquisition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18431 - MoRE: Mixture of Reused Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18176 - Q-BIOLAT: Binary Latent Protein Fitness Landscapes for QUBO-Based Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.27526 - Where Grokking Happens: Distributed Utility and Fourier Recoding Without a Module Switch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17571 - Mixed-Integer Nonlinear Differentiable Predictive Control for Underground Pumped Hydro Energy Storage Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17964 - CompileRover: Revolutionizing Virtual Machine Compiler Optimization with a Tri-Role LLM-Driven Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19004 - Sparse Bayesian Modeling of EEG Channel Interactions Improves P300 Brain-Computer Interface Performance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17772 - Temperon: Full-Time SAM Quality at a Third Less Wall-Clock Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17575 - Reasoning through Evolution: Automatic Meta-path Discovery for LLM-based Fake News Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18597 - TRIPROBE: Probing Task Separability Beyond Classification for XAI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18525 - RoboVAD: A Large Cross-Domain Evaluation Benchmark for Anomaly Detection in Robotic Arm Manipulation Videos Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17843 - Toward Composable Network Digital Twins: A Subgraph-Based Latency Prediction Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18704 - Composite-Gradient Learning for Shared Control Authority Between Deep Reinforcement Learning and Model Predictive Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17697 - Orthogonal Ensembles and Tested Explanations for Performer-Independent Body-Motion Emotion Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02510 - A Calibrated Instrument for Measuring How Inference Optimizations Affect Output Quality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18005 - A unified framework for global and local interpretability using adaptive derivative-ordered random explanation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17171 - Disentangling Long-Term Memory via Latent Neuro-Symbolic Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18461 - Prior-Free Competitive Ratios for Improving Bandits: Scale, Curvature and Horizon Are Free, but Not Jointly Under Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17595 - DSD: Learning Diverse and Reusable Motor Skills via Diffusion Skill Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17682 - FAME: An FPGA-Based Platform for Approximate Multipliers Evaluation with Pattern-Guided DNN Retraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17730 - Trajectory Learnability for Offline On-Policy Distillation with Imperfect Teachers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18321 - Physics-based prediction, uncertainty quantification and decision-making for IN718 crystallographic texture intensity across LPBF defocus regimes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18863 - Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18587 - Suppressed, Not Erased: A Representational Trace of Edited Facts Survives Even Weight-Free Knowledge Editing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18985 - Principled Koopman Representations with Kalman Inference for Efficient Time-Series Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17815 - Goal-oriented probabilistic forecasting for dynamic PRB allocation in 5G networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17297 - CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18779 - Preventing Model Collapse: A Fisher-Rao Perspective on the Dynamics of Training with Synthetic Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18878 - Hyperbolic Graph Representation Learning for Differential Diagnosis on Biomedical Knowledge Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18481 - A General Kernel Framework for Non-CND Distance Measures Using |D|-Dimensional Sparse Landmark Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19083 - Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19128 - Learning Fractional-Order Dynamics from a Single Trajectory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18127 - Breaking the $T^{2/3}$ Barrier for Sequential Calibration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.13668 - Enhancing Physics-Informed Neural Networks with Domain-aware Fourier Features: Towards Improved Performance and Interpretable Results Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02948 - Physics-Informed Neural Networks for Fast Multilayer Spectral Inversion of H{\alpha} 6562.8 A and Ca II 8542.1 A Spectra Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18025 - BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.01912 - The Missing "I Don't Know": Why Three Reasoning-Reliability Findings Converge on Calibrated Abstention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17686 - vidax: A Unified JAX Framework for Video Generative Models on Accelerator Meshes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18077 - Patch the Distribution Mismatch: RL Rewriting Agent for Stable Off-Policy SFT Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11220 - EdgeReMIND: A Scalable, Top-Ranked Memorization Baseline for Temporal Multi-Relational Link Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17916 - How Many Labels Does Model Choice Need? Certificates and Budgets for Selective Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18622 - Integrated Optimization of Automated Warehouse Operations and Last-Mile Transport for Differentiated On-Demand Delivery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19048 - Decentralized Optimal Equilibrium Learning Over Dynamic Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17601 - Stability-Constrained Approximation in Spline KANs: Exact Layer Balancing and Budget-Compatible Saturation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17619 - Rank and computation of the pathlifting Jacobian of a DAG ReLU network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18682 - How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19107 - Evidence-Grounded Agentic Formulation Development in an Autonomous Laboratory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19099 - Long-Context Demonstration Selection Using State Space Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17888 - Leveraging Complementary Embeddings for Replay Selection in Continual Learning with Small Buffers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08336 - Structural Inference under Hidden Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18045 - PACT: Can Enterprise AI Assistants Be Trusted Under Pressure? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18605 - Prism-SQA: An Interpretable and Adaptable Neural Framework for Surface Electromyography Quality Assessment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12724 - TwinMark: A Unified Watermark for Provable Survival Under Feature and Logit Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19011 - The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18560 - From 'May' to 'Is': Certainty Distortion in Language Model Rewriting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07951 - Beyond Embedding Transfer: Component Roles in Grokking Transfer and Stability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18078 - Where Should Agents Live? Energy-Memory Characterization of Agentic AI for the Edge-Cloud Continuum Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18283 - Decoding Extrahepatic Targeting of Lipid Nanoparticles with Interpretable Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17721 - Multi-Appliance Non-Intrusive Load Monitoring via Label-Preserving Aggregate Recomposition and Prediction Consistency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18315 - Pay Only for Disagreement: Certified No-Regression Verdicts for Model Updates with Matching Label-Complexity Bounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17560 - Beyond Pixel Similarity: Task-Aware Evaluation of GAN-Based Synthetic Sonar Data for Robotic Perception Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18100 - Calendar-Structured Sparse Principal Component Analysis for Interpretable Multi-Periodic Electricity Consumption Profiles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06060 - Limits of Transfer Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2006.12694 - Performance and Complexity Trade-off Optimization of Speech Models During Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13704 - Lecture notes on Physics Informed Neural Networks, Neural Operators, and their applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17638 - Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.27409 - Stable Filters for Generative Modeling of Graph Signals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18759 - Adaptive hybrid coupling with operator inference, the overlapping Schwarz alternating method and reinforcement learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17837 - Probabilistic Linear Explanations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19077 - RLLBC-Lib: An Educational Code Library for Reinforcement Learning and Learning-Based Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19074 - Deep Divide-and-Reduce in Symbolic Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02628 - Variational Approach for Job Shop Scheduling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00408 - DRL-AdaPart: DRL-Driven Adaptive STAR-RIS Partitioning for Fair and Efficient Resource Utilization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.06868 - On Finite-sample Concentration of Median of Incomplete U-Statistics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00661 - AMIGO: Agentic Multi-Image Grounding Oracle Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28662 - Spectral-Target Physical Latent Structuring for JEPA-Style World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04264 - When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18745 - Generalizing Adam to Manifolds for Efficiently Training Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2305.16901 - DPG loss functions for learning parameter-to-solution maps by neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.18773 - Sharp margin-based generalization bounds for realizable SVM Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17845 - On Dominant Manifolds in Reservoir Computing Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.05967 - Correcting Boundary Bias and Observation Independence in Bayesian Experimental Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01898 - TabPFN-3.5: Technical Report Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17895 - Information Geometric Self-Organization at the Edge of Stability in High-Capacity Kernel Associative Memories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16827 - The parity gap in crystal tensor prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18714 - Simple-regret rates and minimax optimality of fixed-prior expected improvement in Mat\'ern and squared-exponential RKHSs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.29245 - Beyond the Previous Layer: Residual Predictive Structure in Sparse MoE Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17940 - TTM-Bench: A Framework for Text-to-Music System Performance Benchmarking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18585 - Characterizing Replay Retention Under Dynamics Shift in Model-Based Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18167 - Procedural Pretraining for Molecular Property Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17831 - GeoCrossBench: Cross-Band Generalization for Remote Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.02831 - SAiFE-gym: Model-based Environments for Automated Market Making with Concentrated Liquidity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17788 - Comprehensive reconstruction of collider events with hypergraph representation learning and graph-conditioned diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18928 - TuiML: Machine Learning for AI Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17984 - VLA-ULAP: Interleaving Cloud VLA Calls with Ultra-Lightweight Local Action Prediction at the Edge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18663 - FoundAna: A GNN-assisted Foundation Model for Graph Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18107 - Learning to Program Adaptive Non-Local Observables for Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18655 - Beyond Direct Sensing: Harnessing Indirect Observations from Third-Party Sensors in Vehicle Tracking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18173 - Riemannian Deep Learning: Modules, Networks, and Geometries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19305 - The Attention Within: Consensus Dynamics in Selective State Space Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17997 - Post-Training in Time Series Foundation Models: A Unifying Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20002 - Learning Lyapunov Operators for Nonlinear Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18894 - A Comprehensive Review of Generative Physical Artificial Intelligence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18111 - Fourier Analysis of Parametrized Interactive Quantum Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17991 - Explainable Graph-theoretical Machine Learning with Application to Alzheimer's Disease Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.16286 - A Convergence Framework for Deep $V$-Learning: Error Propagation and Sharp Action-Gap Bounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18782 - Stochastic Dimension Zeroth-Order Estimator: Stable and Memory-Efficient Training of PINNs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.24002 - Acting in Meters: Learning Metric Interactions for Precise Robotic Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18243 - Bridging the Gap in ECG-Based Emotion Recognition: A Unified Evaluation of Deep Learning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15055 - Debiasing Text-to-Image Evaluation via Implicit Cultural Alignment Reward Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15740 - PitchFlower: A flow-based neural audio codec with pitch controllability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.25566 - Beyond Static RAG: An Adaptive, Tri-Metric Routing Framework for Efficient Long-Context Inference on Commodity GPUs Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.17564 - Reliable Virtual Sensing: A Multi-Domain Benchmark for Robustness Under Sensor Failures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18396 - Physics-Informed Sylvester Normalizing Flows for Bayesian Inference in Magnetic Resonance Spectroscopy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.03590 - Online Robust Reinforcement Learning Through Monte-Carlo Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18599 - CoRe-MARL: Cooperative Redistribution Under Unknown Dynamics Using Recurrent Multi-Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18639 - How to Compress KV Cache in RL Post-Training? Shadow Mask Distillation for Memory-Efficient Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06850 - Multi-Task Learning for Sparsely-Labeled Time Series: A Case Study on Cold-Hardiness Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09062 - Generic Characteristic-Zero Equivalence Between Derivative B\'ezout Inversion and Multipoint Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17578 - A Multitask Large Reasoning Model for Molecular Science Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.12808 - Persistent Magnitude Homology for Quantitative Equational Theories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21479 - APGEM: Adaptive Policy-Guided Error Mitigation for Quantum Reinforcement Learning on a Real-World CVRP Case Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18219 - iMINDBench: iEEG Multi-Institution Neural Decoding Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18104 - Robust and Efficient AI Frameworks for Scalable Material Design and Property Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17646 - Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.11507 - F-DACE: Fuzzy Disagreement-Aware Causal Evidence Fusion for Abstention-Safe Conversational Retail Decision Support Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18238 - ReDIL-GNN: Resynthesis Domain Incremental Learning for Circuit Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18595 - Higher-order pruning of experts in mixture-of-experts language models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18916 - Disentangling Algorithmic Bias from Archival Artifacts: A Controlled Audit of Vision-Language Model Valuation in Metropolitan Museum Archives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17572 - Reaching Every Position Without Searching: Rotating Sparse Wiring on the Hypercube as a Substitute for Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18145 - Fast Learning Rates for Physics-Informed Kernel Methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18901 - Provable Guarantees and Efficient Learning of Structural Equation Models with Latent Confounders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18535 - TERN: A Delta-rule Memory with a Seasonal Reference and Online Adaptation for Epidemic Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18407 - Steering Interference Reflects the Model's Defaults, Not the Behavior Directions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06951 - FairLRF: Achieving Fairness through Sparse Low Rank Factorization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.16549 - MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09206 - Safety-Flag: A Unified Benchmark for the Reliability and Calibration of LLM Content Moderators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19072 - The Operable Pareto Front: Distilling Offline Search into Run-Time Control for Multi-Objective UAV Edge-Computing Scheduling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17992 - Democratizing Clinical Tumor Whole Genome Sequencing: 18-hour End-to-end Analysis via Trillion-parameter Large Language Models Locally Deployed on Consumer-grade Hardware Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17620 - QEMScore: How Much Does the Measurement Add to Learned Quantum Error Mitigation? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17896 - FedGuide: Diffusion Prior Alignment and Value Baseline Guidance for Heterogeneous Federated Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18964 - Double descent is the principle of least action Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19076 - Matching Multi-Loop Complexities with a Single Loop: Optimal Optimization Stationarity and Best-Known Game Stationarity in Nonconvex--Concave Minimax Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17973 - REVERSAL-BENCH: A Reversibility Axis and Reset Oracle for Measuring the Reset-Free RL Cliff Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17745 - FPGN: Redefining Ultra-Fast Programmable Gate-based Neural Acceleration with Differentiable LUTs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08427 - SAM-on-the-Curve: Sharpness-Aware Mode Connectivity for Robust Weight-Space Interpolation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17748 - Timbre Analysis of the Hulusi, a Southwestern Chinese Free-Reed Instrument, using Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17612 - WaveTLM: Reliable Time-Series Language Modeling through Task Compilation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18812 - Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18860 - QuanText: Protecting Dataset-Level Secrets in Textual Data Sharing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17995 - Reliable learning in challenging environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2304.03370 - NeuroECG: ECGFounder-Based Deep ECG Representation for EEG-Free Neurological Prognostication After Cardiac Arrest Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18891 - EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16692 - Butterfly Effect and the Kinetic Energy Cascade in Probabilistic Machine Learning Weather Prediction Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18489 - Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18708 - The Automaton Underneath: The Additive Input Pathway Is a Parasitic Attractor for State Tracking in Householder Linear RNN Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18966 - MCLC-NET: Multimodal Continual Learning for Leaf Counting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18129 - Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19101 - Accurate Trace Estimation with Fewer Random Bits via Recursive TensorSketch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18577 - FedPGT: Progressive Gradient Transmission for Vehicular Federated Learning over Time-Varying Channels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18089 - RecMorph: Topology-Guided Spatial Recurrence for Generalized Morphology Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18359 - Can VLMs Reliably Assess Sidewalk Accessibility Attributes from Pedestrian-Level Imagery? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17882 - Data Efficient Any Transformer-to-Mamba Distillation via Attention Bridge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.19266 - An operator splitting analysis of Wasserstein--Fisher--Rao gradient flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.18060 - Interpretable Patch-Based Deep Learning for Wildfire Spread Prediction from Ensemble Simulations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18555 - Curvature-aware Expected Free Energy as an Acquisition Function for Bayesian Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26339 - Multi-Objective Hyperparameter Search via Damped Gauss--Newton Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2401.03580 - Beyond Truncation: Rethinking LLM Decoding as Ensemble Pruning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18723 - Understanding the Staged Dynamics of Transformers in Learning Latent Structure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.19328 - Which Histories Matter for Time Series Forecasting? Learning Predictive Relevance with Future Supervision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23221 - Learning Kernels by Alignment for Multiclass Bayes Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06474 - LSR-Net: Learning the Forward Evolution Operator for Nonlinear Fluid Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19039 - REQAP: Resilient Weight Packing and Quantization for Edge DNN Acceleration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17555 - Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17909 - No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17550 - On the Identifiability of Mixed Ordinal and Exponential Family Causal DAGs under Linear Parametric Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17942 - LightSleepX: A Lightweight, Inception-Based Dual-Modal Network for Sleep Staging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19062 - ActiveScale: Scaling Active Perception for Robots across Model, Data, and Hardware Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18514 - The Free Inference Dimension: Complexity Measure for Zero-Collision Navigation under Hypothesis Mixtures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17816 - Finite-Sample Unbiased Variance of MMD under Unbalanced Sampling: Exact Estimation and Quasi-Linear Computation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13874 - Approximation of the Basset force in the Maxey-Riley-Gatignol equations via universal differential equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08194 - Not All Layers Need Tuning: Diagnosing and Directing Adaptation in Vision-Language-Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18084 - Hybrid coupling with numerics-informed neural networks and the overlapping Schwarz alternating method Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17841 - Semantic CSI Feedback for Beam Selection: When Task-Aware Embeddings from Sparse Pilots Outperform Full-Bandwidth Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18368 - Prior-matched evaluation of operational Earth-observation classifiers: a three-number reporting method demonstrated on Sentinel-1 internal-wave detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07146 - VISTA: Validation-Informed Trajectory Adaptation via Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12044 - Math for AI safety: an invitation for mathematicians Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15289 - NeuroSketch: A Practical Design Recipe for Neural Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.09524 - Tackling Failure Modes of PINNs and PIKANs Using Conflict-Free Gradients Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14841 - Behavioral Fingerprinting and Navigation Prediction in Web Browsing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18273 - Changepoint-Aware World Models: Detecting Dynamics Shifts and Recovering by Forgetting Stale Replay in Model-Based RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18950 - Making Political Text Scaling Comparable: Infrastructure and Hyperparameter Sensitivity for 17 Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17602 - AfriSyCo: Measuring Assertive Framing, Verification, and Wording Sensitivity Around African-Language Content Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17853 - Rethinking Domain Specialization for Open-Ended Scientific Reasoning in Astronomy Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17644 - A Geometric Theory of Decision Boundaries in Structured Markov Decision Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18610 - Walking the Score Manifold: Continuous-time Generative Dynamics on Learned Data Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17901 - Bracketing Uncertainty in Clustering Under the Manifold Hypothesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17892 - TACTICS: Taxonomy-Aware Intelligent Corpus Sampling for Machine Translation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17956 - A Four-Stage Decomposition of Word-Problem Solving and Mechanistic Fragility in LLM Math Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17804 - Every Fixed Metric Has a Blind Spot: A Learned Atmospheric Critic for Scoring Forecast Realism Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18381 - FuseFi: Combining Irregularly Sampled CSI from Diverse Communication Packets and Frequency Bands for Wi-Fi Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.22143 - Visual Cue Guided Video Planning for Generalizable Robot Navigation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16737 - LIGE-GR: A Smooth Leap from Ranking to Generative Recommendation in the LLM Era Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.18148 - Subspace-Decomposed JEPAs: Disentangling Progression and Content in Latent World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.31111 - The Uneven Impact of Generative AI on Student Learning: Examining the Roles of Reliance, Evaluation Literacy, and Course Policy in AI-related Courses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18676 - Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17653 - Weakening Neurons: An Input-Output Functionality in Transformers with Outsize Influence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18612 - Gradient Descent with Stochastic Subspaces via Persistence of Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18416 - The Unbearable Weight: Scaling Models and Methods for UAV Audio Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17884 - A Gradient Flow Approach to Solving Inverse Problems with Latent Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.19276 - Transformation Laws in Neural Representations: Structure, Realisability, and Construction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18190 - Robust Ultra Low-Bit Post-Training Quantization via Stable Diagonal Curvature Estimate Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13806 - Behavior2Value: Benchmarking and Empowering LLMs for Consumer Value Measurement from E-commerce Behaviors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18203 - Maximum Strong Independent Sets in Hypergraphs: Reductions, Bounds, and Greedy Certificates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17951 - One Axis, No Brake: Self-Knowledge Limits the Filtering of Harmful Peer Conformity in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18998 - R\'enyi Tracking Bounds for Langevin Dynamics with Moving Targets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17577 - Rethinking How We Evaluate Methodological Progress in Health AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18134 - Learning Interaction Kernels from Collective Steady States Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12004 - Geometry of learning dynamics: Gradient descent versus natural gradient on the ridge of optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16805 - Forecasting Individual NetFlows using a Predictive Masked Graph Autoencoder Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.20483 - Solving Conic Programs over Sparse Graphs using a Variational Quantum Approach: The Case of the AC Optimal Power Flow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.00341 - Reinforcement Learning for Real-Time Vision-Language-Action Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18207 - A GAN-Based Framework for Robust DDoS Attack Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18281 - Symmetry without a manifold: intrinsic dimension on orbits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17926 - Interpretable Multi-Instance Learning Enables Early Prediction of Key Molecular Alterations from Routine Flow Cytometry in Acute Myeloid Leukemia Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18825 - Bumblebee: Interleaved Mixed-Layer Building Blocks for Large-Scale Recommendation Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24804 - Efficient Robust Learning at the Information-Theoretic Limit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17655 - Optimizing the Preconditioner: A Black-box Online-to-Nonconvex Conversion with Static Regret Minimization Oracles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.17607 - Derivative-Free Structured Updates for Muon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17759 - Adaptive Anisotropic Attention for Axis-Structured Signals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08788 - Fallacy Benchmarks Measure Scheme Recognition, Not Fallacy Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18644 - Bergson: An Open Source Library for Data Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11660 - Machine learning kinetics from molecular dynamics data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17736 - Accelerating Diffusion Sampling via Speculative Draft Trees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17691 - A Lightweight CNN Integrated Compact Convolutional Transformer for Multi-Scale Feature Learning and reducing computational complexity for breast cancer mammography image detection and classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18212 - Subjective Risk Decomposition: A New View for Uncertainty Quantification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15196 - ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17943 - Wasserstein Formulation of Reinforcement Learning. An Optimal Transport Perspective on Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14765 - Scalable Music Cover Retrieval Using Lyrics-Aligned Audio Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.11262 - The Latent That Never Was: A Forensic Re-run of the CVAE Ablation in Action Chunking Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16745 - Capability Emergence Can Be Forecast: Per-Seed, In Advance, With Calibrated Intervals, Certified False Alarms, and a Blind Pre-Registered Gate Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19000 - Learning Contact Dynamics through Touching: Action-conditional Graph Neural Networks for Robotic Peg Insertion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.12151 - Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03994 - NObSP: Functional Decomposition of Neural Networks via Oblique Subspace Projections Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17825 - Social Laws for Multi-agent Coordination in Stochastic Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18929 - Tabular Deep Learning vs Classical Machine Learning for Urban Land Cover Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19010 - Fathom: Per-Query Read Depth for Sparse Decoding over Offloaded KV Caches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17652 - Unleash LLMs Potential for Sequential Recommendation by Coordinating Dual Dynamic Index Mechanism Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2409.09253 - Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18320 - Topology-enhanced machine learning for speech signal processing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2311.15210 - BLADE: ReliaBle Dynamic Hardware-Aware SNN-ANN Boundary SeLection for Event-BAseD Object DEtection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17562 - Bayesian Quadrature Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16218 - LargeMonitor: Monitoring Online Task-Free Continual Learning via Large Pretrained Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09430 - Peak-Aware Short-Term Load Forecasting Across Distribution Grid Aggregation Levels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18588 - COMPASS-ABS: Reducing Fragmentation in Shared GPU Clusters for Deep Learning Training Workloads Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18519 - Self-Supervised Learning for Robust Resonance Mass Regression in Cascade Decays Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17726 - Dataset-Dependent Effects of Cross-Depth Aggregation and Soft-Routed Experts in EEG Foundation Model Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17886 - HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13954 - Structure is not mechanism: high-gain gated-FFN rows across text and genomic foundation models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17599 - Learning Nuclear Structure with AI: Radii and Collectivity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17838 - Visual Perception Engine: Fast and Flexible Multi-Head Inference for Robotic Vision Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.11584 - Agora: Git as Shared Memory for Collective AutoResearch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18094 - PrimeScientist: Strategic Allocation of Research Effort in Autonomous Research Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17846 - Anomaly Detection in General Ledger Data: Results from a Hybrid Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18228 - Preservation of Log-Concavity and Convergence of Wasserstein-Fisher-Rao Gradient Flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18118 - A Survey on Bridging EEG Signals and Generative AI: From Image and Text to Beyond Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.12048 - Uncertainty measurement for complex event prediction in safety-critical systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.01289 - Synthetic Electric Vehicle Charging Session Generation Using a Conditional Variational Autoencoder Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17808 - StableEval Arena: A Cost-Aware Agentic Benchmark for Stablecoin Price Stability Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18949 - Instrument Classification of Solo Sheet Music Images Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18980