TILens Daily Edition 2026-08-27 Filters: topic=ai, github=hidden Stats: 812 articles, 17 sources, 791 research papers Top topics: AI, AI Research, Python ## News - Previewing the Model Hardware Standard Source: anthropic-blog Topic: AI Labs (+AI) URL: https://www.anthropic.com/news/model-hardware-standard-research-preview - Expanding our support for scientists Source: anthropic-blog Topic: AI Labs (+AI) URL: https://www.anthropic.com/news/expanding-support-for-scientists - Better answers, broader thinking: What students gain from ChatGPT and critical-thinking training Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/what-students-gain-from-chatgpt-critical-thinking-training - LesionIQ skin cancer diagnostic Source: raspberrypi-news Topic: Hardware (+AI) URL: https://www.raspberrypi.com/news/lesioniq-skin-cancer-diagnostic/ - Expanding OpenAI’s presence in Brazil Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/expanding-our-presence-in-brazil - True Positive Weekly #175 Source: true-positive-weekly Topic: AI (+AI Research) URL: https://aiweekly.substack.com/p/true-positive-weekly-175 - Cyborg roaches become tiny paramedics Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/cyborg-roaches-become-tiny-paramedics - ArchUnit Source: jvm-weekly Topic: Java (+AI) URL: https://www.archunit.org/ - Agent Skills Source: jvm-weekly Topic: Java (+AI) URL: https://blog.jetbrains.com/idea/2026/08/agent-skills-in-intellij-idea/ - The Ox Alpha mystery ends with Z.ai Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/the-ox-alpha-mystery-ends-with-z-ai - How to Set Up Python for Machine Learning (The Right Way) Source: python-weekly Topic: Python (+AI) URL: https://www.youtube.com/watch?v=cAtKtvmds1o - AI-Infra-Guard Source: python-weekly Topic: Python (+AI) URL: https://github.com/Tencent/AI-Infra-Guard - Reinforcement Learning for LLMs: The Complete Guide Source: python-weekly Topic: Python (+AI) URL: https://cameronrwolfe.substack.com/p/llm-rl - Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers Source: python-weekly Topic: Python (+AI) URL: https://huggingface.co/blog/train-multi-vector-encoder - VectorSmith Source: python-weekly Topic: Python (+AI) URL: https://github.com/kjgpta/vectorsmith - Nvidia buys Hugging Face 💰, Inside OpenAI 🤖, making LLMs faster ⚡ Source: tldr-tech Topic: General (+AI) URL: https://tldr.tech/tech/2026-08-27 ## Research - Planetary prediction engine: Automating global models via Earth AI Source: google-research-blog Topic: AI Labs (+AI, AI Research) URL: https://research.google/blog/planetary-prediction-engine-automating-global-models-via-earth-ai/ - The Sigmoid Function: From 'e' to Neural Networks Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/the-sigmoid-function-from-e-to-neural-networks/ - I Trained Six Models for Fraud Detection, and the Best One Isn't in Production Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/i-trained-six-models-for-fraud-detection-and-the-best-one-isnt-in-production/ - Agentic AI Is Rewriting The Analytics Stack But There's One Skill It Still Can't Touch Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/agentic-ai-is-rewriting-the-analytics-stack-but-theres-one-skill-it-still-cant-touch/ - How to Work with AI Coding Agents Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-work-with-ai-coding-agents/ - Stop Giving Your AI Agent a Search Box and Start Giving It Typed Tools, Hard Bounds, and a Gate It Cannot Talk Past Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/stop-giving-your-ai-agent-a-search-box-and-start-giving-it-typed-tools-hard-bounds-and-a-gate-it-cannot-talk-past/ - Selective Regenerative Decoding: Trajectory-Level Intervention for Inference-Time Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24338 - STAIN-FL: Stealthy Targeted Attack Injection with Contextual Triggers in Federated Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23952 - Ensemble of Convolutional Neural Networks for StrokePrediction: Towards Improved Diagnostic Accuracy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24771 - Identifying Latent Declarative Representations of Code for Assisting Repository Migration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23619 - ReactBench: A Benchmark for Topological Reasoning in MLLMs on Chemical Reaction Diagrams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.15994 - Do Joint Language-Audio Embeddings Encode Perceptual Timbre Semantics? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.14249 - ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.10068 - EMRB: A Multi-Level Benchmark for Evaluating LLM Reasoning over Raw Electromagnetic Signals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24086 - Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.11482 - MAPLE: MoE Adaptive Plug-and-play Layer-wise Expert allocation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15299 - CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10426 - Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17027 - ToolRobustBench: Stage-Wise Perturbation Evaluation and Failure Diagnosis for Tool-Calling Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23635 - When Can One Neuron Fix Repetition Loops in LLMs? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13705 - Don't Just Listen, Try Planning: Graph-based Retrieval-Generation Agent for Long-form Audio Meeting Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24048 - A Dual-Dimensional LLM Framework for Automated Item Incidental Content Similarity Analysis in Large-Scale Assessments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24825 - Simthesizer: An Agent-Driven Simulation Framework for LLM Serving Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24650 - Algorithmic Impact Reveals the Hidden Social Choice Structure of Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24046 - Beyond Executable Models: The Pufibara Agent Harness and the Modelica Agent Workflow Benchmark for Physical System Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23653 - Meta$^n$: Recursive Self-Improvement through Emergent Depth Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24735 - Mechanistic Circuit Identification for Controllable Data Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24065 - Predicting Radiologist Expertise from 3D Gaze Patterns During CT Interpretation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23836 - Recursive Agentic Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23956 - NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.09473 - MetaRAG: Belief-Action Aligned Policy Optimization for Agentic RAG Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24214 - VGGT-DP: Generalizable Robot Control via Vision Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.18778 - A Mathematical Theory of Interpretation: Rational Entropy, Spectral Readout, and Confusability as a Resource Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23892 - SA-Bench: Evaluating Semantic Alignment in LLM-Based Paper Reproduction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24252 - SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24011 - Reinforcement Learning-Guided Evolutionary Policy Optimization for Preference-Adjustable Heterogeneous Agile Earth Observation Satellite Scheduling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24470 - MediSkill-Evo: Process-Constrained Self-Evolution for Evidence-Grounded Clinical Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23397 - Paritok-4B: Intent-Conditioned Context Compression for Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24188 - Elastic KV Cache for LLM Serving:A Working Reclamation Mechanism, and Why Chunked Prefill Already Closes the Gap Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23658 - When Youth Enter The Chat: An Epistemic Shift in the Validation of LLM-Based Measures of Student Talk Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23780 - Hierarchical Skill Retrieval for Data-Efficient Adaptation of Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24042 - Diverse by Reasoning: Harnessing the Wisdom of LLM Crowds for Future Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24001 - How much of a measured AI preference is the model, and how much is the instrument? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23641 - Across the Loss Landscape with Progressive Growth Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24568 - Matched Excess-Outranker Regularization for Candidate-Set Interference in Continual Knowledge Graph Embedding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24273 - TRACE: An Evidence-Grounded Benchmark for Safety Evaluation of Large Reasoning Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24232 - Beyond Static Interpretability: Anticipating Post-SFT Mechanisms from Pre-SFT Parameters for Better Tuning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24482 - Resilience Matters for Embodied Agents System: New Metrics, Systematic Evaluation, and Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23839 - Seeing vs. Believing: Evaluating the Language Bias of Open-Source MLLMs in Counter-Intuitive Scenes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.07737 - SuperLocalMemory 4.0: The Governed Memory Operating System for AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08253 - Evidence Blindness in Direct Corpus Interaction: Persistent Navigation with AtlasNav Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24764 - ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution Shaping Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24411 - AeroDPO: Unleashing Lightweight UAV Navigation with High-Fidelity Perception and Automated Preference Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07557 - On-policy Distillation with Verifiable Reward Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24696 - FLARE: A Systematic, Uncertainty-Aware Framework for Evidence-Based Adoption of Artificial Intelligence in Healthcare Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23643 - Are Android GUI Agents Robust Against Runtime Anomalies? AnTrap: Evaluating Agents in Dynamic Adversarial Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24099 - Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distribution Shifts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16926 - Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23873 - Granite.Trust Policy Tools: Shareable, Actionable Policies for Generative AI Applications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23870 - Best Practice Critic Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23566 - Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24842 - STRIVE: Multi-Agent Structured Temporal Reasoning with Integrated Verification for Longitudinal Radiology Report Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24237 - ReflCtrl: Controlling LLM Reflection Efficiently via Representation Engineering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.13979 - Poisoning Agentic Alpha: Adversarial Vulnerabilities Across Roles and Architectures in Multi-Agent Trading Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24069 - RAGSentinel: Certifiable Geometric Consensus for Robust Retrieval-Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23965 - SyPS: Measuring Sycophancy Prompt Sensitivity in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23837 - AI Finds A Way Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23875 - 'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24191 - TransPhy: Visual In-Context Learning for Physically Grounded Image Editing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24119 - SANE: State Anomaly Neutralization for Stable Extreme-Context Delta-Rule Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22354 - Evaluating Multiple LLM Generations with Validated Task Coverage Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24228 - Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16645 - PhysMLLMs: Spatial Priors for Unified Referring Segmentation and Grounded Reasoning of Images and Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24574 - Metadata-Aware Adaptation of a Generative Foundation Model for Conditional CMR Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24342 - Neurosymbolic Alignment for Physiologically-Safe Clinical Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24534 - Scalable Question-Centric Text-to-Image Evaluation: Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24112 - RefineRank: Joint Box Refinement and Ranking for Surgical Spatio-Temporal Grounding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23928 - MatReplace: A Reference-Free, Conditioning-Aligned Benchmark for Material Replacement in Interior Scenes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24107 - ACE: A Self-Correcting Agentic Canvas Editor for Multi-Slide Presentation Automation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24103 - FraudBench: Protocol-Sensitive Benchmarking of Adversarial Robustness for Financial Risk Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24551 - Learning the Kohn-Sham map with neural operators for quasi-linear scaling density functional theory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23895 - Lifted Model Construction under Approximate Commutativity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24713 - What You Can't See Is What You Learn: Slot-Selective Evidence Masking Favors Compositional Generalization in Shared-Genome Language-Model Societies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20054 - Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02304 - Panning for Gold: Expanding Domain-Specific Knowledge Graphs with General Knowledge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.10485 - Scalable and Versatile Identification for Hierarchical Structural Causal Models: A New Look at Project STAR Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24500 - CausalCache: Conditional High-Fidelity Restoration for Long-Horizon GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22577 - MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23035 - A Behavior-Guided Online Probabilistic Forecasting Method for Electric vehicle Charging Loads Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24441 - What Guides the Agent? Adjudicating Unauthorized Behavior via Localizing Behavior-Guiding Instructions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24022 - EviDx: Evidence-Aware Active Diagnosis with Scaffolded LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24570 - AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23740 - RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24758 - Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.02520 - Discovering Adaptive Transmission Programs for Collective Innovation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24545 - Rebuild Dossier: Mechanically-Enforced Specs for Agentic App Rebuilds, and What Model-Tier Failures Reveal Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23616 - TabDPT-Turbo: Efficient In-Context Learning for Tabular Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01400 - Parameter-Efficient Self-Supervised Adaptation for EEG-FM under Fixed Computational Budgets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24727 - CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09159 - What Reaches Expert Review? Representation, Structural Screening, and Candidate-Form Dependence in AI-Assisted Item Development Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23766 - ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11048 - Functional compatibility as a determinant of persistent neural learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22462 - More Rejective, Not More Discriminative: The Unit of Verification in Pre-Execution LLM Oversight Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23941 - CIVA: Critic-Induced Value-Subspace Attacks on Visual World-Model Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21114 - A Unified Algebraic Framework for Classification Performance Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04028 - Taming foundation model with invariance-oriented pre-training for broad-spectrum EEG analysis across signal-level, brain-state, and brain-health tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24597 - Function-Level Execution Feedback for Code Preference Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23632 - FARCA: Fact-Aligned Reliability-Aware Credit Assignment for Reinforcement Learning with Factual Supervision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24350 - Robust Code RL via Faulty-Code-Driven Test case Synthesis and Dense Reward Shaping Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24135 - Deep Learning Super Resolution for Satellite Cloud Mask Downscaling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24715 - Right Diagnoses, Decorative Reasoning:A Perturbation Audit of Medical Chain-of-Thought Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24790 - When Less Is More: An Empirical Study of Minimal Responses in Counseling Dialogues and the Behavior of LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24080 - Apodex 1.1: Scaling Agentic Intelligence for Complex Work Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23283 - PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24082 - STA-Net: A Decoupled Shape and Texture Attention Network for Lightweight Plant Disease Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.03754 - Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23329 - Beyond Confidence: Test-Time Scaling for Multi-Turn Search Agents via Retrieval Grounding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24024 - Auditing the Synthetic Memoir: Measuring Scene-Level Confabulation in LLM-Generated Autobiography Against the Documented Record of the Life It Describes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23640 - Monotone and Separable Set Functions: Characterizations and Neural Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.23634 - Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08960 - Intrinsic PAPR: Tackling Misattribution in 3D Intrinsic Decomposition via Proximity Attention Point Rendering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.00500 - Multilevel Fair Allocation under Additive Preferences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24400 - SaliMory: Orchestrating Cognitive Memory for Conversational Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04120 - Auditing an AI-Generated Mathematical Proof: Human Assessment of OpenAI's Quantum Parallel-Repetition Argument Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14673 - MOSAIC: Masked Outsourcing of Secure AI Computations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.29221 - PlaceSeek: Human-Centered Geospatial Retrieval of Urban Outdoor Places via Semantic Grounding and Affective Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24133 - What's the Catch? Evaluating Temporal Consistency in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23474 - Too much of a good thing -- when knowledge distillation promotes overfitting, and how to avoid it Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23752 - Provenance Guided Incremental Learning Under Evolving Concept Definitions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23893 - Method, Mind, and Morality: How People Make Sense of Artificial Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24748 - Eating for a Sustainable Planet: Personalized Sustainable Diet Recommendation via Constraint-Aware Decision-Making Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24274 - Towards Reproducibility in Predictive Process Mining: SPICE -- A Deep Learning Library Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.16715 - Syn2RealTrack: Bridging the Gap Between Synthetic and Real-World Datasets for Online Multi-View Multi-Target Tracking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24130 - Beyond the Mandate: A Systematic Security Analysis of the Agent Payments Protocol (AP2) Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23858 - The Shadow Price of Intelligence: Quality Degradation in LLM Inference as a Supply Chain Problem Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23986 - When May an Agent Stop? Evidence-Carrying Termination for Tool-Using LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23623 - A Judge Should Know What Changed:Construct Validity for LLM-as-a-Judge Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24419 - Do Recipes Have Personas? Characterizing and Generating Creator Style in Attributed Procedural Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24369 - You Can Learn Tokenization End-to-End with Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13940 - Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24876 - Robust Motion Generation using Part-level Reliable Data from Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.12703 - When Seeing Is Not Enough: Benchmarking Interactive Visual Grounding in LVLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23978 - Structured Frequency-Domain Evidence for LLM-Based Time-Series Anomaly Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24113 - BenchBench-Protocol: Evaluating Real-World Wet-Lab Protocol Reasoning and Modification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23898 - Constrained Hyperparameter Optimization for Streaming Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24712 - Evolutionary Recurrent Decision Model in Developing Adaptive and Maladaptive Behaviors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23932 - Restoring Without Forgetting: Continual Learning Across Image Degradations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23799 - LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.05375 - Superintelligent Retrieval Agent: The Next Frontier of Agentic Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06647 - SA-RSQ: A Versatile Sparse Representation Framework for Multi-modal Recommender Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22979 - GraphVid: Interactive Graph-Controllable Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21580 - OPDSearch+: On-Policy Distillation with RL Refinement for Search-Augmented Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24310 - Skill-Conditioned Gated Self-Distillation for LLM Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28791 - The RAT: A Unified Bayesian Model for RAG Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24753 - Topology-Guided Modular Actor-Critic Learning for Continuous Systems under Temporal Objectives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2304.10041 - LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24555 - Exploit More, Explore Smarter for Budget-Constrained Agentic Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23848 - Self-Evolving Scientific Agent Designs Physically-Reasoned Whitebox Fluid Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08405 - Confident at the moment of action: belief miscalibration in LLM play under hidden information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24691 - Automatic Model Card Generation Using an LLM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24807 - Causal Modelling of Support Interventions for Student Competency Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24632 - PatientHub: A Unified Framework for Patient Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11684 - AI Agents Push Humans Out of the Loop Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23642 - An Information-Flow Perspective on Explainability Requirements: Specification and Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.01479 - WebMCP-Phalanx: Enforcing and Characterizing Trust Boundaries for Browser-Integrated LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24017 - Generative AI for Validating Physics Laws Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.17894 - Design-to-Plan: A Large Language Model-Based Multi-Agent Framework for Manufacturing Process Planning from 3D CAD Models and 2D Engineering Drawings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24039 - Reflection with Action-Induced Visual Differences for Desktop GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24015 - The Empire, Long Divided, Must Unite: Architectural Convergence in Three LLM Agent Harnesses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23953 - Rules Before Oracles: Auditable, User-Configurable Argument Selection for Deliberative Polling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23979 - QML for Quantum Sensing under Measurement-Induced Information Loss Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23934 - TangramPuzzle: Evaluating Multimodal Large Language Models with Compositional Spatial Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16520 - Gated Activation Steering for Reducing Sycophancy & Hallucination in Medical Question Answering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23666 - Epistemic Transfer in AI-Assisted Verification: A Framework and Evaluation Protocol Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08882 - Names Can Hurt: Spotting Slopsquatting Risks Caused by Package Name Hallucinations in Local Coding LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23897 - NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23959 - Serving Masked Diffusion LLMs: Characterization and Design Principles from Real Hardware Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23807 - Do LLMs Understand Limit Order Book Dynamics? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23706 - Training a Knowledge Base: Supervised Structure Learning for Agent-Curated Document Stores Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21829 - CAFE: Self-Improving Search Agents Need Co-Evolving Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24794 - Partial Identification under Causal Orders by Linear Programming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24427 - UCO: A Multi-Turn Interactive Reinforcement Learning Method for Adaptive Teaching with Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.08873 - Strategic Exploitation in LLM Agent Markets: A Simulation Framework for E-Commerce Trust Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10059 - Relative Time Intervals Representation for Word-level Timestamping with Masked Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24041 - Review of Explainable Decision Support and Adaptive Human-Machine Interfaces for Automation Transparency in Maritime Autonomous Surface Ships Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.15959 - IterCAD: Iterative Program Repair for CAD Code Generation from Orthographic Views Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24020 - Contrastive Branch Policy Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24300 - LumiXAI: A Modular Full-Stack Framework for Feature Attribution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24524 - Mahalanobis-Based Multi-Head Attention for Complex State Propagation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24462 - TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Servers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23763 - Adaptive Influence Graphs for Failure Attribution in Multi-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24361 - Beyond What Meets the Eye: Unveiling Situational Illusions for Multimodal Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22232 - Disentangled Skill Representations for Predictive Human Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23776 - LLM Agents Perform Controlled Experiments Using Simulation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23622 - Screening Autism Spectrum Disorder in children using Deep Learning Approach : Evaluating the classification model of YOLOv26s by comparing with other models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2306.14300 - Discrete Diffusion Models: A Unified Framework from Tokenization to Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13431 - Outlier-Robust Diffusion Solvers for Inverse Problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09477 - Incorporating Cognitive Load and Knowledge Transfer for Multi-Domain Knowledge Tracing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24005 - CytoNet: A Foundation Model for the Human Cerebral Cortex at Cellular Resolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.01870 - Strictly Causal Streaming Video Anomaly Detection with a Theoretically-Grounded State-Space Core Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24810 - When Do Supervised UQ Ensembles Improve LLM Hallucination Detection? A Robustness Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24492 - A survey detection channel overrides the pixels in an astronomical foundation model, and biases tomographic mean redshifts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23626 - Parason: Revealing Subtask and Trial Parallelism in LLM Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24658 - Can a Dynamic Internal Field Govern a Transformer's Cognition? Certifiability, not Superiority, in Homeostatic Compute Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24319 - AHEAD: Adaptive Hindsight with Environment-Augmented Distillation for Agentic RL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24114 - Preference Optimization for Non-Verbal Vocalization Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24163 - HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.01767 - The Caf\'e in Amsterdam: When the Incumbent Becomes the Oracle Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13393 - Evaluating Deep Multivariate Imputation Models on Wearable Device Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24436 - Real-World Knowledge-Guided Change Data Synthesis for Remote Sensing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24263 - Generating Biomedical Fact-Checking Reports with RL-Enhanced Agentic Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23811 - Is Visual Prompting All You Need? Studying VLM Spatial Reasoning under Progressive Visual Scaffolds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21170 - Constraint-Guided Enterprise Data Mapping with Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24218 - Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09696 - The Mask Is Not the Model: Auditing Prefix Invariance in Attention, State-Space, and Hybrid Sequence Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22876 - Can large language models assist choice modelling? Insights into prompting strategies and current models' capabilities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.21790 - Revelation Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23860 - Constrained Entity Selection under Partial Knowledge for LLM-Based Knowledge Graph QA Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24824 - Task-Adaptive Rubrics for GUI Reward Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24174 - ORBITALIF: An Efficient Spiking Federated Learning Framework for Onboard Cloud Removal Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24073 - Fuzzy Segmentations of a String Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2201.13427 - REFINE: A Multi-Agent LLM Approach for Evidence-Guided Code Refactoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23611 - Memory Is Not Always Needed: Characterizing Conditional Memory in Scientific Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23982 - StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24804 - Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02867 - RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22027 - From Empirical Evaluation to Context-Aware Enhancement: Repairing Regression Errors with LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.13182 - Preference Data Selection for Mitigating the Alignment Tax in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24192 - Macro-Operator Generation and Predicate Selection for TAMP Operator Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23629 - A tale of perfect fit and phantom optima: how data-driven models can fail in real-time optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23885 - Learning to Grade Efficiently: A Bandit-Driven Prompt-Selection Framework for Low-Cost LLM Essay Scoring Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23814 - Quasar: A Programming Language Specialized for LLM Code Actions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.12202 - Mind the Student: Behavioral and Contextual Cues for Automated Engagement Prediction in Online Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24340 - Luce: Relightable Gaussians for 3D Asset Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23943 - ShardMeter: Sharded and Geo-Distributed Training Without the Guesswork Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23840 - HMGCLIP: Heterogeneous Multi-Granularity Contrastive Learning for E-commerce Representation Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24467 - Formal Verification of Romanov's Triplet Logic: A Verified Filter for Sliding-window 3-CNF with Application to Structured Formulas Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18445 - ExploraTwin, a Non-Profit Research Platform for Digital Twin Simulations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20539 - Olapa-MCoT: Enhancing the Chinese Mathematical Reasoning Capability of LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2312.17535 - Adaptive GR(1) Specification Repair for Liveness-Preserving Shielding in Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.02605 - SonarLLM: A Native Sonar--Optical Multimodal Large Language Model for Underwater Perception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24325 - Efficient LLM Collaboration via Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.11578 - EngiAI: Capability-Based Evaluation of Tool-Connected LLM Agents for Engineering Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19743 - How Much Regularization Survives Averaging? Update Masking in Federated Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23286 - Denoising the Future: Context-Aware Spectral Diffusion for Temporal Knowledge Graph Extrapolation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20804 - Maia 200: A Software Defined Dataflow System for Large-scale AI Acceleration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24664 - FedV-KGQA: Multi-Hop Question Answering over Vertically Partitioned Knowledge Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24846 - Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16654 - Optimizing Expert-Designed Crystal Graph Networks for Band-Gap Prediction with an Autonomous LLM Research Loop Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29717 - COCI: Conference Organisers and Content Identifier Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24559 - VLANeXt: Recipes for Building Strong VLA Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18532 - $\texttt{findr}$: Transparent and Fair Credit Risk Decisions through Semi-Structured Regressions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24582 - ER-KANs: Efficient and Robust Kolmogorov-Arnold Networks for Data-Scarce Scientific Machine Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14773 - GenCoord: Skill-Path Commitments under Private Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22055 - Compression Trinity: Exploring Sparsity, Quantization, and Low-Rank Approximations for LLM Compression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24070 - Score-Based Ideal Observer Approximation via Denoising Score Matching for Signal-Known-Exactly Detection Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24768 - Joint Optimization of Tool Creation and Use for Large Language Model Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24571 - StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24777 - Place, Slice and Schedule: Hierarchical O-RAN Control of a Tethered mmWave UAV-gNB Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23824 - msData: A Millisecond-Resolution Network Dataset for Advancing Time Series Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16497 - The Limits of Automatic Evaluation of Creativity in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23705 - Tlow: Flow-based Item Tokenizer for Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24176 - Credit Without Ground Truth: Auditing Step-Level Credit Assignment in LLM Agents Against Executed Replay Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19760 - Discovering Cross-Language Reasoning Invariance in LLMs with Geometry-Invariant Sparse Autoencoders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23809 - In-Context Inpainting for Time Series Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23855 - SENSESHIFT: Continuous Sentiment-Controlled Text Generation via Encoder-based Mask Infilling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24304 - From Causal Plausibility to Causal Reliability: Evaluating LLMs as Calibrated Direct Causal-Edge Classifiers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23660 - Rethinking Pre-Training and Augmentation for Zero-Shot Cross-City Object Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24154 - Co-occurring Associated REtained concepts in Diffusion Unlearning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24192 - EXAM$^2$: $\underline{Ex}tending$ $\underline{A}udio$ $Understanding$ $in$ $\underline{M}ultilingual$ $and$ $\underline{M}ultimodal$ $Analysis$ Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23758 - Not All Tokens Are Equal: Region-Aware Consistency Repair of Backdoors in MLLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24354 - Lightweight GenAI for Network Traffic Generation: Fidelity, Augmentation, and Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25507 - Hybrid Semantic Tool Discovery for Enterprise MCP Gateway: Architecture and Implementation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23992 - A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.20073 - Ad Insertion in LLM-Generated Responses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.19435 - A Literate Programming Environment for Human and Machine Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24644 - Equivariant Covariance Tensors: Guaranteed SPD Uncertainty for Tensor-Valued Geometric Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24386 - ReproAgent: Contract-Guided Paper-to-Code Reproduction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24291 - Housing Potential Common Data Model and City Digital Twin Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05535 - Ethical LLM-Assisted Research: A Framework for Responsible Delegation, Verification, and Epistemic Value Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23644 - StrokeGuard: A Multi-Agent Guided System for Prehospital Stroke Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24555 - Feedback That Backfires: Why Small Language Model Agents Repeat the Call They Just Watched Fail Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23651 - From Gradient-Boosted Trees to Deep Recommenders: Practical Lessons from Migrating a Production Customer Support Recommender Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24132 - ICA: Information-Aware Credit Assignment for Visually Grounded Long-Horizon Information-Seeking Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10863 - RENDER: Controlling Reader-Facing Evidence in LLM Memory Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23568 - Quantifying System-Level Harms from AI Adoption in Complex Sociotechnical Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23906 - Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26958 - EviPathBench: Benchmarking Evidence Acquisition and Reasoning in Vision-Language Models for Whole-Slide Pathology Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19261 - Progressively Learning Heterogeneous Skills in a Unified Latent Space Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23258 - Molecular LLM Agents: From Architectural Design to Scientific Autonomy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23104 - Minima-KV: Retention-Preserving KV Cache Compression with Mixed-Format Paged Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23834 - From State to Action: OODA-Tool for Reliable Multi-Turn Tool Use Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24368 - When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24569 - ExPhy: A Benchmark for Explicit Physical Property Learning in Multi-Object Trajectory Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20009 - The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24358 - Pivot-and-Station Multi-Agent Path Finding: Solvability, Complexity, and Algorithms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24585 - Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23691 - PonderPounce: A Pretrained MLLM as an Episode Context Engine for Robot Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24115 - VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24302 - A Human-Factors Guided Cognitive Model of Visuospatial Complexity in Embodied Active Vision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23572 - Coronavirus Optimization Algorithm: A Success-History Adaptive Evolutionary Framework with Archive-Assisted Search and Stagnation Recovery for Global Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23847 - OmniJudge or OmniBias? Diagnosing Multimodal Judges through Balanced, Decoupled Lenses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24160 - Ollivier-Ricci Curvature of Riemannian Manifolds and Directed Graphs with Applications to Graph Neural Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14211 - RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24275 - Beyond Uniform Local Isometry and Topology: FactoMap for Disentangled Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24762 - LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24845 - Infant Care Video Dataset for Classification of Interventions Using Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23838 - EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02041 - LUCAID: Agentic Multimodal AI for Lung Cancer Precision Pathology Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23803 - Audio-to-Score Transcription using Pre-trained Features, Data Augmentation, and the New SheetSage-A2S Dataset Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06165 - Enhancing Bayesian Optimization and Active Learning Through Kernel Diversity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24721 - SPO++: Stream-Aligned Policy Optimization for Asynchronous Agentic RL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24870 - Retrieval-aligned Tabular Foundation Models Enable Robust Clinical Risk Prediction in Electronic Health Records Under Real-world Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01841 - Confidently Wrong, Silently So: Auditing Undetectable Failures of a Deployed On-Device Language Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23663 - Atomic Units of X: The Compression Layer of Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.12634 - Retrieval-augmented generation vs. deterministic tax computation in multi-agent financial advisory: A 2x2 factorial experiment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23908 - A Formal Methodological Framework for Auditing Robustness and Fidelity in Explainable AI: From Application to Trust Certification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23817 - More GPUs or a Smaller Cache? Tensor Parallelism versus KV Compression for Memory-Bound LLM Serving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23962 - SPAR-Hate: Auditor-Guided Multi-Perspective Role Reasoning for Bilingual Hate Speech Parsing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22018 - Giraffe: A Mapping Architecture from Hidden Text Representations to Visual Embeddings for Efficient Graphic Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23970 - From Corpora to Co-Evolving Capabilities: Capability-Centric Data Design for Generalist Image Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18076 - Automated Synthesis of Cloud Emulators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23842 - RA-CMF: Region-Adaptive Conditional MeanFlow for CT Image Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00901 - A Circuit, Not The Circuit: Non-Unique Causal Localisation of the Mamba-2 State Sink Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00930 - PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01532 - AgentWorld: Personality-Aware Reliability Evaluation for Agentic Information Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24076 - The Dynamics of Intelligence Explosions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14426 - Implicit Q-learning-bootstrapped ant colony optimization for maritime moving-target observation scheduling with agile satellites Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24471 - PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24509 - Balancing Safety and Optimality in Robot Path Planning: Algorithm and Metric Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.23197 - MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23646 - Minimal Decision Dynamics and Contextual Probability: A Quantum Tug-of-War Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.10034 - LLM-Guided Contextual Action Evaluation for Operational Decisions in Industrial Processes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24156 - MARS: Multi-Specialist LLM Relay System for Competitive Programming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23918 - Automata from Agent Traces: Failure and Next-Step Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23670 - TRACE: Transition-Aware Residual Control for Multi-Objective Materials Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23631 - ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24033 - Fidelity Preference, Not Demographic Preference: A Pixel-Level Attribute-Sensitivity Audit of Image Aesthetic/Preference Scorers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23593 - Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.18346 - Data Mixing as Mixture Experiment: Response Surface Methodology and Optimal Design for Large Language Model Pretraining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23922 - Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23391 - 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 - Beyond OAuth: Task-Scoped Authorization for AI Agents via Natural Language Slices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.17170 - Evaluating Language Models on Cross-Language Code Functional Equivalence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23961 - Beyond Accuracy: A Dual-Judge Evaluation Protocol for Vision-Language Models in Legally Grounded Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24258 - PROOF-Gen: From Optimized Data to Better Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23911 - Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03702 - Knowing When to Ask for Help: Bayesian Self-Escalation in Hierarchical LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24087 - VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24063 - EmoTra-TTS: Smooth Intra-Utterance Emotion Transitions for Speech Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23791 - ESQ-Bench: A Multi-Tier Enterprise Oracle Benchmark for Evaluating NL2SQL Dialect Generalization and Silent Semantic Divergence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23569 - Markerless Pose Estimation for Resistance Training Technique Assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24384 - TW-LegalBench: Measuring Taiwanese Legal Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18699 - GRIP: Granular Reward-Guided Parameter Interpolation for Efficient Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25583 - When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25553 - Cross-Dataset Stability of Expert-Informed Skill Prompting and Fine-Tuning for Chinese Metaphor Identification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25579 - Recurrent Neural Networks in Linguistic Theory: Revisiting Pinker and Prince (1988) and the Past Tense Debate Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/1807.04783 - Reliable Financial Named Entity Recognition Under Domain Shift: Confidence Estimation and Selective Prediction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19558 - Padamitra: Grounded Glossary Generation for Classical Sanskrit Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25038 - Distinct dynamics of conceptual and referential disruptions in human reading and large language model processing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25999 - Scalable Supervision for Software Agents via Patch Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.22775 - Conditional Total Correlation and the Serial Depth of Adaptive Parallel Sampling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25505 - Layer-Order Inversion: Rethinking Latent Multi-Hop Reasoning in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.03542 - FrontierChallenge: Evaluating Scientific Workflow Completion Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24979 - Semantic Variability of Replies Across LLMs: Implications for Designing Conversation-Based Assessment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24920 - When RAG Fails to Equalize: Geo-bias in Factual Question Answering over Public Companies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25717 - Clinically Grounded Privacy Evaluation of Medical LMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09590 - A Self-Evolving Multi-Agent Framework Defense against LLM Jailbreak Attacks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26008 - CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08638 - Sell More, Play Less: Benchmarking LLM Realistic Selling Skill Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07054 - Recurrence Meets Transformers for Universal Multimodal Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.08897 - RefLAM: A Reference-Grounded Line Annotation Pipeline for Historical Arabic Manuscripts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25140 - Apples to Apples? Towards Comparable Crosslingual Language Model Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25089 - The Changing Geometry of Grammar: Dimensionality and Neighborhood Reorganization across Transformer Layers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25166 - VietAIDetector: An Open-Source Zero-Shot Detector for Vietnamese AI-Generated Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25478 - Gavel: Agent Meets Checklist for Evaluating LLMs on Long-Context Legal Summarization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.04424 - Provenance Before Prose: Claim-Locked Reporting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25336 - Reasoning or Rambling? Exploring the Effect of Thinking on Agent Persuasion Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.21054 - Just Pass Twice: Efficient Token Classification with LLMs for Zero-Shot NER Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.05158 - AWM: Answerable Working Memory for Long-Document VQA Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25618 - On the Idiosyncrasies of the Mandarin Chinese Classifier System Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/1902.10193 - HealthBench-Psych: A Mental Health Subset of OpenAI's HealthBench Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25071 - Groundhog Bit-Flip Attack: Seeding Infinite Generation Loops in Mixture-of-Experts LLMs through Bit Flips Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25276 - SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15971 - From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25894 - IDEAlign: Comparing Ideas of Large Language Models to Domain Expert Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.02855 - ClueWeaver: Reward-Guided Dual-Agent Evidence Reasoning for Compact LLMs on Literary Long Narratives Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25531 - Retrieval-Augmented Agentic Rubric Generation for Reliable Medical Response Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15161 - Code World Model: Coding Agent as World Brain Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25927 - GGSS: Geodesic-Gated Spherical Steering for Inference-Time Debiasing of Generative Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25375 - The Invisible Editorial Layer: Formalizing Undisclosed Inference-Time Steering, Probability Placement, and the Attribution Problem in Deployed Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24662 - AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26004 - Corpus2Skill: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14572 - Mind2Report: Expert-Level Commercial Report Synthesis via Cognitive Deep Research Agent Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.04879 - 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 - Controllable Affective Generation via Latent Vector Steering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25569 - TranslatePsy-AfriSLM: High-Quality Data Scaling For Low-Resource Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18655 - ReliableRAG: Combating Misinformation in Retrieval-Augmented Generation via Reliability-Guided Reasoning Chains Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25487 - Tool Verification for Test-Time Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02203 - Think-Probe-Respond: Improving Large Language Models as Judges of Research Idea Novelty Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25660 - Beam Search, Self-Consistency, and the Limits of Inference-Time Scaling for Grammar-Constrained Text-to-SQL in Small Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25761 - Rethinking the Multilingual Reasoning Gap with Layer Swap Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26735 - Plans You Can Check: Verifier-Grounded Learning of an Open-Weight Planner for Executable Video-Editing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25622 - AgentDiff: Meaning-Bearing Rewrites Trigger Deeper Divergence than Presentation Changes in LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25981 - Query-Side Attacks on GNN-Based KGQA: Tracing Failures from Entity Linking to Answer Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25922 - Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgeting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25115 - EduAgentQG: Multi-Agent Personalized Mathematics Question Generation with Explicit Diversity and Objective-Aware Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.11635 - Formal, Executable and Explainable Runtime Monitoring of Spoken Air Traffic Control Operational Procedures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25926 - LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06087 - VDAR-Router: Adaptive LLMs Routing via Verbalized Query Difficulty Analysis Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18098 - InternBootcamp: Boosting LLM Reasoning with Verifiable Task Scaling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.08636 - Reconstructing the Right Episode: Evaluating Interleaved Conversational Memory Beyond Long Context Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25655 - Unveiling Spectral Mechanisms in Training-Free LLM Text Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25944 - From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25605 - CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25500 - EduDial: Constructing a Large-scale Multi-turn Teacher-Student Dialogue Corpus Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.12899 - Mitigating LLM biases toward spurious social contexts using direct preference optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.02585 - SCHEDBench: A Benchmark for Evaluating LLM Constraint Faithfulness in Natural-Language Combinatorial Scheduling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00991 - Generative vs. Encoder Large Language Models for ASR Evaluation: A Comparative Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25574 - Short Horizons and Sparse Concepts: a Mathematical View of the Readout in the J-lens Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25347 - Fine-Tuning Whisper for Automatic Speech Recognition in Baniwa: A Preliminary Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26060 - OmniPhys: A Unified Multimodal Benchmark for Physics Understanding and Generation from Chinese Educational Corpora Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25398 - SimLens for Early Exit in Large Language Models: Eliciting Accurate Latent Predictions with One More Token Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.17618 - Leveraging Speech Acts for Low-Data and Cross-Domain Conversation Derailment Forecasting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25359 - Rare Diseases, Common Dilemmas: LLMs Prioritize Equal Resource Distribution over Patient Benefit in Decision-Making Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25236 - Learning What to Share and What to Personalize: Hierarchical Strategy Co-Evolution for Agent Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25329 - AEL: Evolving Agent Harness in Open-Ended Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21725 - ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.09062 - MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.06156 - Localize-Then-Decide Guarantees for LLM Judgments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25824 - MoganBert-TR: A Turkish Encoder Foundation Model Trained from Scratch with a CLM-to-MLM Curriculum Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25768 - A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19660 - Anchoring Bias in LLM-as-a-Judge Systems: Prior Scores Compromise Evaluation Independence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25869 - Overview of SHROOM-Visions 2026: A Shared Task on Hallucination Detection in Large Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25662 - EgoArgus: Benchmarking VLMs as Situational Assistants for Modality-Grounded User Supports Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25561 - Natural Language Input, Semantic Track Representation, and LLM Inference: Making the Maritime Information Exchange Model Tractable Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24892 - Style Wins, Substance Loses: A Diagnosis of LLM-as-Judge in Idea Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01666 - Beyond Local Surprise: Grounded Dialogue as Selective Belief Revision under Referential Uncertainty Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26035 - Routed Graph Handoff: Adaptive Format Selection for Multi-Agent LLM Delegation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25277 - Synthesizing Instruction-Tuning Datasets with Contrastive Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13538 - A Primer on Computational Semantics for Artificial Intelligence Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25022 - PonsRAG: A Pons-Inspired RAG Bridging Cognitive Islands for Coordinated Long Narrative Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25486 - Trilingual Topic Modeling of Sri Lankan Parliamentary Debates Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20365 - Lower-Resource, Higher Scores: Language Bias in LLM Evaluators Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.14480 - Can We Read the Mind of an Audio LLM? A Verbalizable, Multilingual Middle-Layer Workspace Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24958 - Clarify User Expertise: Towards Proactive Conversational Agents Tailoring Responses to User Proficiency Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22266 - KESA: A Knowledge Enhanced Approach For Sentiment Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2202.12093 - Loss-Based Active Learning for Neural Abstractive Summarization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25881 - 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 - Memory Augmentation Unlocks Efficient Chain-of-Thought Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21265 - Align Then Adapt: Label-Efficient Adapter Learning for Asymmetric Dense Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.03403 - TOPAS: Workflow-Aware Prefix-State Scheduling for Multi-Agent LLM Serving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25523 - PlanSightRAG: A Visual-First Multimodal RAG for Automating Question Answering and Compliance Checking for Civil Standard Plans Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26091 - SelfGraphRAG: Bridging the Supervision Gap in Graph-Based RAG with Synthetic QA Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25123 - Retrieve, Match, Escalate: Accurate and Scalable Product Linking with VLM-Distilled Cross-Encoders and Agentic VLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25037 - Addressing the Reasoning Gap: Mechanistic Circuit-Based Knowledge Editing in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.05876 - From National Curricula to Cultural Awareness: Constructing Open-Ended Culture-Specific Question Answering Dataset Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.04632 - When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11612 - LITERARYBIGFIVE: Author-Personalized Text Generation in a Unified Interpretable Space Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23124 - Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11632 - Cross-lingual Biography Enrichment via Claim Extraction and Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23390 - GUIDE: Generative Unsupervised Chinese Query Correction via Phonetic and Visual Shared-ID Encoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25343 - Belief Cascades Drive Persuasion in LLM Agent Networks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25152 - One Form to Transfer Them All: Pretraining Multilingual Language Models Beyond Native Orthography Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25904 - Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.11544 - SwarmWorld: Stigmergic technological evolution in societies of language-model agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26081 - AutoVerifier: Residual-Guided Non-Parametric Optimization for Reference-Based Answer Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25637 - Unmatched Does Not Mean False: Incomplete Reference Sets Can Reverse Calibration Rankings in Open-Ended Theory-of-Mind Tracking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25654 - When Retrieval Helps and Distracts: Evaluating Evidence-Generating LLMs for Biomedical Claim Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01409 - E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.22733 - Pigeonholing: how bad prompts hurt models, causing collapse and mistakes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24267 - FinRiskAtlas: Decision-Aligned Evaluation of Large Language Models for Financial Risk Review Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25325 - MathAdv: What Theorem Provers Know, Reason, Formalize, and Generalize Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25449 - The "Curse of Knowledge" in LLM Query Simulation: Concept Provenance for Tracing Answer-Side Intrusion Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25245 - Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.25721 - MTDiag: A Multi-Turn Diagnostic Dataset Towards Clinically Meaningful LLM Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25085 - LLMTrace: A Corpus for Classification and Fine-Grained Localization of AI-Written Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.21269 - Trace Integrity for LLM Data Agents: A Vision for Auditable Structured Reasoning in Real-World Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26036 - From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02559 - ResMerge: Residual-based Spectral Merging of Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02252 - VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Following Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26013 - DCGC: Draft-Conditioned Global Correction for Complex Reasoning with Masked Diffusion Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25428 - Adaptive Triggering for Bias Correction in LLM Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25379 - Mitigating Rubric Interference in LLM Judges via On-Policy Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14684 - Learning New Facts with QLoRA: An Acquisition-Retention Frontier Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25677 - Prefix Sliding for efficient test-time scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26070 - Reconstruction of Personally Identifiable Information from Proprietary Data in Supervised Fine-Tuned Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12264 - JEPA-x: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24044 - Continuous Adversarial Flow Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.11521 - The Imperfective Paradox Is Not Necessarily in Large Language Models: A Benchmark Failure Before a Model Failure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25005 - Beyond Dense Adam States: Adaptive Log-Space Quantization for Memory-Efficient Optimizers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22322 - Key Point Analysis Needs Structure Recovery: Task Definition, Dataset Diagnosis, and a Structure-Aware Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25854 - Non-Asymptotic Bounds for Closed-Loop Identification of Sub-Exponentially Growing Nonlinear Stochastic Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.04157 - Robust CurveMoE: Multi-Norm Adversarial Defense for Mixture-of-Experts Models via Mode Connectivity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26043 - Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16296 - Autonomous Cyber Defense: Real-Time Attack Detection and Mitigation in Software-Defined Networks Using Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22075 - Uncovering the Limits of Proof Sharing for Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19351 - Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15062 - FedCC: Towards Addressing Label Distribution Skews in Distillation-Based Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23031 - Model-Agnostic Open-Set Air-to-Air Visual Object Detection for Reliable UAV Perception Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.09297 - Smooth $\%$MinMax: A Differentiable Relaxation for Codon Harmonization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03881 - GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30865 - One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25936 - Gradient-based Sample Selection for Faster Bayesian Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.07742 - Joint Initialization of Flux Networks and Effective Multiplication Factor for Physics-Informed Neural Networks Solving Neutron Diffusion Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25443 - Learning Mixtures of Plackett-Luce Models for Multi-Objective Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25200 - Rotary Position Encodings for Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.22259 - Understanding the Energy Scaling of Large Language Model Inference Across Context Lengths and Attention Architectures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25096 - Generalized Riesz Regression: A Unified Framework for Debiased Machine Learning with Riesz Representer Fitting under Bregman Divergence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.07752 - Why and When Neural Networks Improve Local Approximation in Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24963 - Multi-output Gaussian process prediction of physical fields under linear equality constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25709 - A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25643 - Clinical Graph-JEPA: Predictive Patient-State Knowledge Graphs for Cognitive Decision Support Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22583 - ROMNet: a hybrid reduced order modeling and machine learning approach to waveform inversion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25160 - DAW: Dynamics-Aware Weighting for Deep Learning Forecasts of Chaotic Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22277 - A Hierarchical Synergistic Deep Learning Framework Integrating Composition, Structure, and Ionic Transport for Solid-State Electrolyte Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25592 - Trojaning the Alignment: Stealthy Backdoor Attacks against Graph Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20991 - Neither Precision Nor Architecture Alone: Controlled Tests of Failure Remedies for Physics-Informed Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25327 - Cluster-Dags as Powerful Background Knowledge For Causal Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.10032 - When Does Context Routing Help? A Systematic Study of Multi-Modal Fusion in Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25128 - Lowering the Barrier to AI-Driven Inspection: A No-Code Workflow for Automated Structural Defect Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25176 - Demystifying Reinforcement Learning Post-Training of Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24949 - Towards A Unified Information Bottleneck Framework for Time Series Explanations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25897 - Adaptive Bayes exactly tracks information over intrinsic time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08789 - Adaptive Regularization for Random Features: A Neighboring Early-Stopping Rule with Oracle-Rate Guarantees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25513 - A General-Purpose Framework for Chemical Reaction Representation with Atomic Correspondence and Flexible Condition Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.17629 - When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25941 - Beyond Pairwise Feedback: Listwise Vision-Language Supervision for Preference-Based Reward Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25350 - ONNX-Net: Towards Universal Representations and Instant Performance Prediction for Neural Architectures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.04938 - Loss Landscape Geometry of Partial Differential Equation Emulators: Or, Symmetry Learning via Gradient Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.20172 - Are LLM-Enhanced GNNs Privacy-Safe? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25727 - TrustFormer: Cross-Temporal and Cross- Dimensional Transformer for Task-Specific Multi-Dimensional Trust Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25238 - Multi-Modal Anomaly Detection: A Survey Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24937 - MODE: Modality-Decomposed Expert-Level Mixed-Precision Quantization for MoE Multimodal LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17118 - ICON Decomposition: Multivariate Concept-Level Explanations of Deep Representations for Model Auditing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26083 - Representing MAX functions using two-hidden-layer ReLU networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25221 - BVR Sim: An Open and High-Throughput Environment for Heterogeneous Air-Combat Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25419 - Individual Fairness in Hierarchical Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25586 - MeMark: Membrane-Space Watermarking for Spiking Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25738 - Cooperative Multi-Agent Reinforcement Learning for Adaptive Aggregation in Semi-Supervised Federated Learning with non-IID Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25794 - IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24588 - Efficient Estimation of High Information Projections using Nearest Neighbours Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25887 - NVExplain: Explaining Time Series Forecasting with Latent Trajectory Analysis and Structure-Preserving Surrogates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25080 - TTSR: Test-Time Self-Evolving via Reflection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03297 - From Idea to Prototype in an Afternoon: Scaffolded, AI-Assisted Rapid VA Prototyping Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31311 - CRAMER: Control via Request-Aware Masking for Editing Recommenders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25370 - FlowMoDL: Model-Based Deep Learning with Conjugate-Gradient Data Consistency for Highly Accelerated 4D Flow MRI Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25828 - Frequency-aware forecasting for short-term typhoon gust prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25604 - WAVE: Reversing the Guidance Hierarchy for Coarse-to-Fine Guided Depth Super-Resolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25302 - Trust the Mass: Forced Weights in KV-Cache Eviction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25230 - Two Dimensions Govern Agnostic Multiclass Transductive Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25326 - Canalization Before Generalization: Grokking as a Dynamical Probe Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25813 - TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26086 - Rethinking the Transferable Adversarial Attacks and Robust Defense in Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25133 - Adaptivity via a Parallel Architecture for Stochastic Gradient Methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28902 - FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25158 - Theoretically Principled Federated Learning for Balancing Privacy and Utility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2305.15148 - A Storage-Retrieval Gap in Parametric Knowledge Graph Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25489 - Decomposing Gradient Suppression in Barren Plateaus: Activity, Sign Organization, and Coupling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.01319 - Thermodynamic cost of inference and learning in physical neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.09980 - The Frame Kernel Method for Multiscale Operator Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25084 - Bayesian Flow Networks for Offline Trajectory Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25163 - GRAPE: Gradient Refinement and Progress-Aware Exploitation for Query-Efficient High-Dimensional Bayesian Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25116 - Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.15857 - Minimax Alternating Regret for the Experts Problem and Online Convex Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25182 - Why Does Graph Learning Fail to Fully Benefit from a Text Teacher? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25741 - CropCop: An Auditable 120-Class Plant-Health Model from Benchmark Reconstruction to a Quantised Runtime Artifact Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25539 - DualOPSD: Adaptive Privileged Teachers for On-Policy Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26019 - Unsupervised Post-Training of Foundation Models: A Survey Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24982 - Interpreting Protein Language Model Embeddings via Orthogonal Projection for Protein Fitness Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25548 - Cross-Domain Transfer with Particle Physics Foundation Models: From Jets to Neutrino Interactions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12364 - EncoTESS: Age-Sensitive Encodings from Raw TESS Light Curves Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25019 - ExFold: Unified Expert Folding for Training-Free MoE Prefill-Decode Acceleration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24938 - Distance Is Not Enough: Forget-Retain Alignment Gap Predicts LLM Relearning Robustness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25429 - HCC+: Hyperbolic Guarding for Certified Attention Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24971 - When Does Frequency Decomposition Benefit Physics-Informed Neural Networks? A Preliminary Ablation Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24940 - Fairness-Aware Test-Time Prompt Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25707 - Evidence-Grounded Mapping of Multimodal Human Sensing Psychological Transdiagnostic Dimensions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24903 - CardioFusion-AI: Robust ECG--PPG Fusion for Multimodal Physiological Monitoring Under Signal Degradation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26000 - ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.00188 - RoboMME-Interference: Benchmarking Robot Memory Under Interference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22338 - Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamW Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25535 - Three-Way Open-Set Detection for Robust Autonomous Navigation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.15343 - Rollout-Decoded Reconstruction for Long-Horizon Prediction in Latent World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25017 - FRAME: separating sampling variation from representational cause in medical imaging fairness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25981 - Large Language Model Few-Shot Prompting with Dilemma Training Outperforms Human Surrogates in Predicting Patient Preferences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25771 - MSR-IVA: Masked Structural Residual Independent Vector Analysis for State-Aware Fusion of Structural MRI and Dynamic Functional Network Connectivity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24978 - Transforms for LLM Quantization: The Great Inversion and Format Co-Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25188 - Generative Modeling by Minimizing the Wasserstein-2 Loss Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.13619 - Detection != Reliable Control: Decodable Empathy Directions Yield at Most Partial Shifts in Automated Empathy Scores Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24901 - Fast rates in Bayesian online learning with approximate posteriors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25706 - AFDBench: A Reasoning-First AI Scientist for NationalWeather Service Forecast Discussions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24954 - Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25826 - Clearing the Underbrush: AI-Enhanced RF Interference Suppression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24974 - When Probing Accuracy Saturates, Fragility Resolves: A Complementary Metric for LLM Pre-Training Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11375 - How Much Rank Does LoRA Need? Rank-Error Bounds for Transformer Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26052 - On the Representational Geometry of Dynamic Programs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25034 - Adversarial Training of Linear Models under Stealthy Attacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25681 - The Von-Neumann State-Space Transformer for neural decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25088 - Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25735 - From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25243 - Phase-Consistent Magnetic Spectral Learning for Multi-View Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18728 - Modeling spatio-temporal locality in multi-step forecasting of geo-referenced time series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25698 - DataKernelBench: Can LLMs Optimize Database Queries on GPUs? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25061 - Forecasting Weather-Driven Price Dynamics Across Sri Lankan Tea Market Catalogues Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24894 - OpenSanctions Pairs: Large-Scale Entity Matching with LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.11051 - Multi-Turn Reasoning LLMs for Task Offloading in Mobile Edge Computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07148 - D$^3$-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24987 - Narcissus: Program Synthesis Using Context-Aware LLM Approximations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25657 - Generative Modeling: A Review Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.05458 - JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25593 - GreenLeaf Law Embed Tiny: A Compact Embedding Model for Legal Domain Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24936 - Reflection Steering: Disentangling Reflection from Reasoning in Activation Space for Token-Efficient Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25542 - TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22788 - Skill Issue: Are Skills Language-Invariant in LLMs? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25832 - Virgil: Navigating Explainability for Transformer-based Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25555 - AlgoTrace: Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.15987 - Imitation Learning for Connection-Tableau Construction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26009 - Provable Privacy Attacks on Trained Shallow Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.07632 - Data-driven Effective Modeling of Stochastic Chemical Reaction Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25421 - LILAC: An Idempotent Neural Speech Codec Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05727 - Continually learning neural-operator surrogate for three-dimensional airborne electromagnetic Bayesian inversion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25932 - Physics-Informed Foresight Pruning for Sparse PINN Solvers of Nonlinear PDEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25564 - Online Pandora's Box for Contextual LLM Cascading Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07392 - EXAONE Tabular 1.0 : Technical Report Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25774 - Improved Analysis for Hessian-free High-resolution Monte Carlo Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25052 - Emergent Abilities in Large Language Models: A Survey Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.05788 - Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.00282 - Scorpio: Serving Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.23022 - Comparing Corrupted Constrained Learning Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25745 - Towards Reliable, Generalizable, and Specific In-Context Knowledge Editing via Multi-Objective Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25100 - Training Alignment Auditors via Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25460 - Spatio-temporal dual-stage hypergraph MARL for human-centric multimodal corridor traffic signal control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17068 - Refusal geometry reflects refusal training: diverse refusal prefixes can raise stable rank and weaken refusal vector ablation attacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25390 - Simultaneous inference of environmental and interaction forces in collective dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25181 - Drift Variation Autoencoder: Unifying Generation and Representation Learning through Conditional Posterior Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25138 - Learning to Prompt: Improving Student Engagement with Adaptive LLM-based High-School Tutoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20138 - A meta-algorithm for ab initio reconstruction of complex mixtures in cryo-EM Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25388 - MacroAgent: Regularity-Aware Macro Legalization with LLM-Agent-Designed Contour Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24946 - VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26105 - LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25204 - SAUSS: Stochastic Approximation with Unbiased Simulated Scores for Limited Dependent Variable Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25304 - CountTRuCoLa: Rule Learning for Interpretable Temporal Knowledge Graph Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.09474 - What Should a Large Language Model See? Physical Invariants as a Data Representation for PDE Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25189 - Optimal Time Complexity Algorithms for Computing General Random Walk Graph Kernels on Sparse Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.10368 - Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24977 - SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01990 - How Robust Are Automated Fact-Checking Systems? A Cross-Benchmark Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25934 - Maximum-Volume Nonnegative Matrix Factorization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04795 - DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22067 - A Layer-wise Analysis of Supervised Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.11838 - FedQoS: Federated QoS-Risk Learning for Heterogeneous Indoor-Outdoor Access Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25496 - Planetary Prediction Engine: Autonomous Geospatial Prediction via Intelligent Data Selection and Foundation Model Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26088 - VINCENT: Validated Interaction Network for Cross-drug Explanation of Therapeutics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25841 - Geometry-Constrained Kolmogorov-Arnold Networks: Learning Edge Geometry via Banach Duality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25807 - Hyperbolic Latent Geometry for Tree-Structured Prototype Networks: A Local-vs-Global Trade-off Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25199 - Advancements in Content-Based Image Retrieval: A Comprehensive Survey of Relevance Feedback Techniques Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2312.10089 - Resource-Efficient Pruning for Transformer via Low-Rank Importance Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24973 - JEPAMatch: Geometric Representation Shaping for Semi-Supervised Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21046 - A Comedy of Estimators: On KL Regularization in RL Training of LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.21852 - Temporally Centered SIGReg Improves LeWorldModel Representations for Robot Policy Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.26924 - Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24988 - Neural-Bayesian Structure Learning for Discrete Choice Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25258 - Predicting Time Pressure of Powered Two-Wheeler Riders for Proactive Safety Interventions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.03173 - Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28500 - LDAC-Net: A Learnable Multi-Lag Differencing Attention-Convolution Network for Drift-Robust Recognition with Low-Cost MOX Gas Sensors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25646 - Learning to summarize user information for personalized reinforcement learning from human feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.13579 - Finding and using interpretable latents in a neutrino foundation model with sparse autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26090 - CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24947 - Edge-Local and Qubit-Efficient Quantum Graph Learning for the NISQ Era Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16018 - Simulating Cognitive Smart Freight Corridors with Agent-Based Models and Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25193 - SCALE: State-Calibrated Latent Embeddings for JEPA Planning in the Right Geometry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16287 - Long-Term Behavioral Evaluation for Trusted Collaborator Selection via Bidirectional Mamba Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25232 - ClayBuddy: A Framework, Evaluation, & Mitigation of Coding Agent Failures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19380 - Deep greedy unfolding: Sorting out argsorting in greedy sparse recovery algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.15661 - Multi-Source Complex Network Reconstruction via Wasserstein Distributionally Robust Optimization and Algorithm Unrolling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19914 - Contrastive Learning for Interpretable Anomaly Detection at Collider Experiments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.13652 - Reinforcement Learning on Benign Facts Amplifies Leakage of Memorized Private Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21727 - TokEval: A Tokenizer Evaluation Suite Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18062 - Scalable Self-Supervised Learning for Multiphase AC-OPF in Distribution Systems with Topology Reconfiguration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25095 - Cubit: Token Mixer with Kernel Ridge Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06501 - Scalable Multi-GPU Simulation of 3D Multicellular Growth with RNN-Based Workload Balancing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25890 - TailSFT: Filtered Fine-Tuning Improves Post-Training Performance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25756 - Token-Oriented Semantic Communication with Pretrained Vision Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25410 - Escaping Low-Dimensional Overlap: Multi-Task Model Merging via High-Dimensional Sparse Disentanglement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25354 - BanglaMamba: Exploring State Space Models for Bangla Fake News Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25190 - Learning from waste: Machine Learning for health risk prediction and computer vision-based sorting in Ghana Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25759 - Towards a theory of inference-time alignment with unknown rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15402 - SHSP: Structure-Aware Hierarchical Solution Prediction for Mixed-Integer Linear Programming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25282 - Mitigating False Credit Propagation: Probabilistic Graphical Reward Aggregation for Rubric-Based Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03361 - Amplifying, Not Learning: The Price of Out-of-Distribution Generalization in AI-Text Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21653 - Machine-learnable Sets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.28947 - StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.15416 - Controlling for Omitted Variable Bias in Deep Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25930 - Towards Robust and Scalable Density-based Clustering via Graph Propagation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00390 - Common-Center Geometry and Certified Radial Reconstruction for Energy-Form Full Conformal Regions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24964 - ShuttleArena: Interpretable Self-Play in Physics-Based Badminton Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25246 - $R^3$: Training Robots to Reason in Natural Language via Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26053 - AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.14313 - Emyx: Fast and efficient all-atom protein generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19377 - Performance uncertainty in medical image analysis: a large-scale investigation of confidence intervals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17103 - Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30837 - Inverse Design of Inorganic Compounds with Generative AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.11827 - M-Fibration Theory with Applications to Neural Network Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25598 - A Theory of Speciation in Generative Diffusion Models on Compact Riemannian Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23798 - Mitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25267 - Riemannian Attention Mechanisms for Transformers: A Theoretical Framework and Architecture Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01283 - Beyond Point Predictions: Uncertainty-Aware Satellite Poverty Mapping for Public Policy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23322 - Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26069 - Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25592 - Beyond Tokens: Probing Higher-Order Epistasis in Learned Protein Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24953 - Beyond Optimal Rates in Stochastic Optimization: Trajectory-Adaptive Stopping Rules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25551 - A Multi-View Coupled Tensor Decomposition for Lightweight Online Adaptive Traffic Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25498 - Quantum-Inspired Modeling of Driving Behavior Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25907 - Modality Contribution Score - A Per-Patient Framework for Quantifying the Relative Diagnostic Contribution of Structural MRI and Amyloid PET in Alzheimer's Disease Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24931 - Scaling Muon for Diffusion Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20818 - It's a matter of timescale: non-linear utility in successor features and multi-objective planning and learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25723 - Same-Player Verification for Account Consistency in Counter-Strike 2 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24893 - EDGE: Experience-Distillation for Guided Exploration in Agentic Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21946 - Noise Contrastive Estimation-based Matching Framework for Low-Resource Security Attack Pattern Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2401.10337 - DeltaGNN: Graph Neural Network with Information Flow Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.06002 - Minimalist Visual Inertial Odometry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19990 - AERIS: Offline Policy Improvement for Multi-UAV Integrated Sensing and Communication Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25477 - iFlip: Iterative Feedback-driven Counterfactual Example Refinement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.01446 - Activation-Space Order-Swap Geometry: A Site-Asymmetry Audit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25315 - Multimodal Injury Risk Prediction in Tennis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25126 - Dynamic Influence-Weighted Distillation for Single-IMU Activity Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24904 - Measuring the Dependency Gap: Diagnosing Inter-Column Fidelity in Tabular Generative Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21636 - Output Dilution: Redundant but Fragile Representations in MoE Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25231 - Generative Action-Chunk Sampling for Adaptive Stiffness Control in Physical Human-Robot Collaboration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25284 - Lost but not erased: Finding traces of a forgotten language in neural speech models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25976 - Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17415 - Drift-Aware Multimodal User Representation Learning via Multi-Scale Temporal Modeling and Sparse Mixture-of-Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25773 - GRIP: Algorithm-Agnostic Machine Unlearning for Mixture-of-Experts via Geometric Router Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16905 - A General-Purpose Molecular Foundation Model Transfers Across Diverse Olfactory Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25893 - Unsupervised Anatomical Feature Learning via Diffusion Models: Enhanced Medical Image Segmentation with Denoising Diffusion Probabilistic Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25693 - FAMPWQ: Fisher Information-based Adaptive Mixed Precision Weight Quantization for Effective LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24945 - Ban&Pick: Enhancing Performance and Efficiency of MoE-LLMs via Smarter Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.06346 - DCEO: Direct Causal Effect Optimization for Long-Term User Value Modeling in E-commerce Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25635 - Functional linear regression from sparse to dense designs: a pooling-ridge method and minimax optimality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25468 - DeMMO: Longitudinal and Cross-Disease Modelling of Digital Mobility Outcomes via Multi-Task Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25073 - A Constitutive Markov Physics-Informed Neural Operator (MPNO) for Autoregressive Stability in Transient Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25744 - SciMIF: Understanding Multimodal Instruction Following in Scientific Domains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25973 - Offline Reinforcement Learning for Hemodynamic Management of Sepsis in the ICU: a MIMIC-IV Study with Dual Off-Policy Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16482 - Infer Human's Intentions Before Following Natural Language Instructions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2409.18073 - Quantum Scrambling Born Machine Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17281 - InsightSR: Refining Symbolic Regression Search Spaces via Parallel Semantic and Structural LLM Guidance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25291 - Resolving Multi-Modal Regression by Difference-Quotient-Based Clustering:Fast Coarse Conditional-Label Assignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25467 - Prefix-Denoising Consistency: Test-Time Verification for Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25311 - Behind the [MASK]: Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25028 - Physics-Informed Error Field Learning: A Post-Training Optimization Framework for Physics-Informed Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24970 - Adaptive Hybrid Subspace Levenberg Marquardt Algorithm with Adequacy Monitor for Large Scale Least Squares Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25524 - Beyond Scaling: Self-Evolving LLM Agents for Hardware Kernel Optimization via an Experience-Driven Workflow and Experience Graph Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25570 - How Edge of Stability Hinders SCAFFOLD in Federated Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25873 - CEDAR: Controlled and Event-Driven Demand Forecasting via Residual Decomposition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25871 - Multi-View Trust Evaluation for Collaborator Selection via Evidential Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25235 - Agentic Autoresearch for Cell-Edge Power Control: Radically Redefining the Researcher's Role Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26093 - SNAP-KG: Streaming Node Assignment via Projection for Knowledge Graph Entity Integration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25149 - Flower Hub: A Reproducible Benchmarking Platform for Federated Learning in Simulation and Deployment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25114 - Evolutionary chemical learning in dimerization networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.14006 - Precipitation Downscaling Using Foundation Model-Conditioned Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25858 - Learning to Act While Waiting: RL Finetuning of Generalist Robot Policies Under Inference Latency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23831 - Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.26865 - LM-X: Explainable Action Modeling with Progress, Event, and Uncertainty Prediction for Generalist Robot Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25757 - Tropospheric temperature and humidity profile retrieval from Meteosat Flexible Combined Imager based on deep learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25700 - Loop Corrections in Random Feature Models: Training Error and Generalization Gap Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12827 - MotoSafety: Edge-AI with Learned Temporal Importance for Two-Wheeler Collision Risk Assessment Under Time Pressure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17823 - TacForcing: Streaming Action Generation with Execution-Time Tactile Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25798 - BAGEL: Adversarially Constrained Online Convex Optimization under Separation Oracle Access Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.16744 - Epistemic Memory: A Validity Layer for Self-Maintaining Intelligent Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.16899 - Differentiated Aggregation to Improve Generalization in Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2404.11754 - Why ML-based cough models do not generalize: a systematic cross-dataset evaluation for tuberculosis screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25846 - MetaSieve: Faster Relational Deep Learning through SQL-Based Metapath Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25903 - PaSta: Noisy Node Classification with Partial Label Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25365 - SAMpLE: A SystemC-AMS Machine LEarning-based Framework for Virtual Prototyping Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25910 - Ladder Up, Memory Down: Low-Cost Fine-Tuning With Side Nets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.14237 - Toward Machine Learning with the Unit as a Primitive: Learning from Unit-Linked Events Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25118 - MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and Coaching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26094 - Energy Yield and Lifetime Climate Classification via Machine Learning for Optimizing Photovoltaic Module Design and Materials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25448 - Forecasting Multiple Observables with SCROLL: Score-Trained Uncertainty for Stochastic Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25898 - AI/ML Life Cycle Management for Interoperable AI Native RAN Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.18538 - PA-CoT: Profile-Adaptive Chain-of-Thought for Personalized Nutritional Consulting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24907 - Sample Margin-Aware Recalibration of Temperature Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.23492 - The Dialect Tax: Dialectal Biases Persist throughout the Language Modeling Pipeline Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24952 - StablePDENet: Enhancing Neural Operator Stability through Physics-Informed Residual-Sensitivity Regularization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.06472 - BRIDLE: Generalized Self-supervised Learning with Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.02118 - Activation Steering Transfer to Agents: One Gain Ratio Does Not Identify Potency and Efficacy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09156 - Learning Continuous Regional Temperature Fields with Lead-Time and Resolution Queries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25823 - Analytical and Bootstrap Confidence Intervals of Double Machine Learning: Simulation studies and an application to rural-urban difference in obesity prevalence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.29456 - Spectral Allocation: Why Muon Outperforms Adam, and How to Improve Muon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25990 - Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09263 ## Community - Breaking Claude Code Opus 5 Auto Mode Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Aug/27/breaking-claude-code-opus-5-auto-mode/ ## Media - JetBrains | Rust Foundation AI Livestream Series - Building AI applications in Rust Source: youtube-rustfoundation Topic: Rust (+AI) URL: https://www.youtube.com/watch?v=cEdw04FR0DU - 7 AI agent patterns to improve your coding workflow Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/watch?v=Z9WbG3m7Da4 - What "real-time voice AI" actually means Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/shorts/RsmKGpJ1we4 - GitLab + OpenAI Codex: Fixing Rust Bugs with Terminal AI Agents Source: youtube-gitlab Topic: Open Source (+AI) URL: https://www.youtube.com/watch?v=YBG14uE1gW8