TILens Daily Edition 2026-08-25 Filters: topic=ai, github=hidden Stats: 734 articles, 20 sources, 710 research papers Top topics: AI, AI Research, Python ## News - How to evaluate LLMs before production Source: github-blog Topic: Open Source (+AI) URL: https://github.blog/ai-and-ml/llms/how-to-evaluate-llms-before-production/ - Funding better evaluations of AI’s impact on wellbeing Source: anthropic-blog Topic: AI Labs (+AI) URL: https://www.anthropic.com/news/wellbeing-research-grants - 5 ways to upgrade your home decor with Google Search Source: google-ai-blog Topic: AI Labs (+AI) URL: https://blog.google/products-and-platforms/products/search/home-decor-tips/ - Granite 4.2 LLMs: How They're Built Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/ibm-granite/granite-4-2 - Amazon EC2 M8i and M8i-flex instances are now available in Canada West (Calgary) region Source: aws-whats-new Topic: AWS (+AI, PostgreSQL) URL: https://aws.amazon.com/about-aws/whats-new/2026/08/ec2-m8i-m8i-flex-canada-west/ - Ramya Ravi: 2026 PSF Board Election Candidate Interview Source: pyfound-blog Topic: Python (+AI) URL: https://pyfound.blogspot.com/2026/08/ramya-ravi-2026-psf-board-election.html - Ee Durbin: 2026 PSF Board Election Candidate Interview Source: pyfound-blog Topic: Python (+AI) URL: https://pyfound.blogspot.com/2026/08/ee-durbin-2026-psf-board-election.html - Benjamin Manning: 2026 PSF Board Election Candidate Interview Source: pyfound-blog Topic: Python (+AI) URL: https://pyfound.blogspot.com/2026/08/benjamin-manning-2026-psf-board.html - Agata Skamruk: 2026 PSF Board Election Candidate Interview Source: pyfound-blog Topic: Python (+AI) URL: https://pyfound.blogspot.com/2026/08/2026-psf-board-election-candidate.html - Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/MultiverseComputingCAI/quantization-aware-healing - The full stack behind abundant intelligence Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/the-full-stack-behind-abundant-intelligence - Jalapeño’s first results show industry-leading speed and efficiency in AI inference Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/jalapeno-first-results - Wire It, Run It, Deploy It: AI Workflows in Gradio Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/gradio-workflow-guide - Disrupting a new covert influence campaign from Russia Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/disrupting-malicious-uses-of-ai-influence-campaign-russia - Introducing the Admin plugin for ChatGPT Work and Codex Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/introducing-admin-plugin - pg_statviz 1.2 released with PostgreSQL 19 support and new features Source: postgres-news Topic: PostgreSQL (+AI) URL: https://www.postgresql.org/about/news/pg_statviz-12-released-with-postgresql-19-support-and-new-features-3369/ - Everyone Says "Agentic AI." Almost No One Means the Same Thing! Source: ai-agents-simplified Topic: AI (+AI Tools) URL: https://aiagentssimplified.substack.com/p/everyone-says-agentic-ai-almost-no - Finding Nemo(Claw): Networking Issue Allows for LLM Poisoning in OpenClaw Source: darkreading Topic: DevSec (+AI) URL: https://www.darkreading.com/cyber-risk/nemo-claw-networking-llm-poisoning-openclaw - How to Steal an AI Model’s Private Thoughts Source: bytebytego Topic: Architecture (+AI) URL: https://blog.bytebytego.com/p/how-to-steal-an-ai-models-private - Apple's Mac mini makes AI comeback Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/apple-mac-mini-makes-ai-comeback - The SpaceX-Nvidia partnership heads for orbit Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/the-spacex-nvidia-partnership-heads-for-orbit - I spent a day at a robot “carnival” in Shanghai. Here’s what I saw. Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/08/25/1141907/dispatch-shanghai-humanoid-robot-carnival/ - Staff Augmentation for AI Infrastructure: Engineers Who Can Actually Ship LLM Systems Source: ardan-labs Topic: Go (+AI, Rust) URL: https://www.ardanlabs.com/news/2026/staff-augmentation-for-ai-infrastructure/ ## Research - AgentHands: Generating interactive hand gestures for spatially grounded agent conversations in XR Source: google-research-blog Topic: AI Labs (+AI, AI Research) URL: https://research.google/blog/agenthands-generating-interactive-hand-gestures-for-spatially-grounded-agent-conversations-in-xr/ - A New Towards Data Science: A Faster Site and a Brand-New Contributor Portal Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/a-new-towards-data-science-a-faster-site-and-a-brand-new-contributor-portal/ - I Deployed My Data Pipeline to AWS. Then Everything That Was “Local” Broke. Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/i-deployed-my-data-pipeline-to-aws-then-everything-that-was-local-broke/ - Recursive CTEs: SQL’s Hidden Graph Traversal Engine Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/six-degrees-of-sql/ - Cross-lingual Biography Enrichment via Claim Extraction and Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23390 - Time Present and Time Past: Benchmarking Large Language Models on Temporally Evolving Document Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08512 - Diagnosing Capability Preservation and Task Sensitivity in Memory Augmented Document Classifiers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.06582 - ForeTime-VLA: Causal Future-Token Distillation from a World Action Model for Conveyor-Belt Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20735 - Task-Driven 3D Printability Assistance via Geometry- and Knowledge-Grounded LLM Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22128 - Reinforcing the World's Edge: A Continual Learning Problem in the Multi-Agent-World Boundary Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.06813 - DiaRelay: Relaying Dialogue Context with a Constant-Size Memory for Emotion Recognition in Conversation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22745 - EDGE: Experience-Distillation for Guided Exploration in Agentic Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21946 - Runtime Action Interference for AI Control of AlphaStar in StarCraft II Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21398 - CONTRAMEM: Learning Self-Evolving Procedural Memory from Contrasting Multi-Model Trajectories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22533 - Counterfactual Transition Graphs: Evaluating Cross-Class Transition Quality Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23164 - Physics-Constrained Deep Learning Model for Contactless Blood Pressure Monitoring from Triaxial Bodyseismography Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23562 - Reasoning Shortcuts and Value Symmetries: What Symmetry Permits, Architecture Realizes, and Optimization Selects Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10420 - SAEM: Stage-Aware Expert Management for Memory-Efficient MoE Inference in Chain-of-Thought Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21614 - COLORA: Efficient Fine-Tuning for Convolutional Models with a Study Case on Optical Coherence Tomography Image Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.18315 - ParallelWorld: Test-Time Scaling for Embodied Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22971 - DeMixPert: Decomposed Response Modeling with Gaussian Mixtures for OOD Single-Cell Perturbation Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23114 - Machine Learning Assisted Inverse Design of Pixelated mmWave Patch Antennas Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23469 - The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.25108 - SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23493 - Object-Uni: A Unified Model for Object-Centric Spatial Understanding and Controllable Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22757 - FinAcumen: Financial Multimodal Reasoning via Self-Evolving Experience Memory Harness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17642 - KONTOGRAPH: Verified Point-in-Time Feature Consistency and Amortised Explanation for Real-Time Anti-Money Laundering under a 200 ms Decision Budget Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22389 - Backdoor Sentinel: Detecting and Detoxifying Backdoors in Diffusion Models via Temporal Noise Consistency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01765 - Language Chain in Alignment: Cross-Lingual Ranking Preference Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23149 - ATP-Bench: Towards Agentic Tool Planning for MLLM Interleaved Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.29902 - TO-Agents: A Multi-Agent AI Framework for Subjective Preference-Guided Topology Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21622 - StrategyBench: Evaluating Explicit Strategy Induction in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23475 - NetConfArena: An Executable Benchmark for LLM Agents in Closed-Loop Network Configuration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23179 - Ask or Answer: A Decision Framework for Multi-Turn Health Misinformation Intervention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21721 - Think with Structured Grounding: Perceptual Reinforcement Learning for Chart and Visual-Tabular Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22429 - RIACT: A Responsible AI System for Personalized Study Habit Tracking and Early Burnout Signal Detection in University Students Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21379 - Online design of dynamic networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.08875 - From Recognition to Reasoning: Advancing Multimodal Harmful Meme Detection via Chain-of-Thought Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.18919 - Zero knowledge verification for frontier AI training is possible Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05433 - Beyond Surface Cues: Disentangling Sociocultural Signals in Multilingual LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23026 - Time Series Forecasting via Reasoning: A Slow-Thinking Approach with Reinforcement Fine-Tuned LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.10630 - Distinguishing Revision and Delayed Elaboration in Incremental Narrative Interpretation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21364 - Length-Adaptive Decoding for Masked Diffusion Machine Translation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22274 - FIDES: A Concordance Protocol for LLM-Generated Trading Strategies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23308 - KSE-Web: An Analysis of Hybrid Retrieval and LLM-Assisted Query Expansion for Low-Resource Khmer Semantic Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21365 - LitReview Arena: Evaluating Literature Review Agents with Battle-Style Peer Review Platform Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21374 - A Survey Instrument to Assess Students' AI and Generative AI Knowledge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21391 - LLMs for Survey Text Analysis - A Performance Comparison Between Humans and GPT-5 on Inductive Content Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22417 - TransHands: Repurposing Human Pose Encoders as Hand Pose Encoders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22341 - FedCC: Towards Addressing Label Distribution Skews in Distillation-Based Federated Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23031 - SSE-Bio: A Structured Self-Evolving Agent with Agentic Retrieval Policy for Multi-Hop Biomedical Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22132 - Correcting a learned physical invariant improves world-model rollouts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23526 - Evaluation Awareness in Language Models: Representation, Verbalization, and Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21766 - From Generation to Simulation: How Far Are World Models from Being True Simulators? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23070 - PolyChirp: Multi-Species Birdsong Classification Using TinyML on Low-Power Acoustic Sensors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23101 - 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 - Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10949 - SSDi8: Accurate and Efficient 8-bit Quantization for State Space Duality Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21952 - NoTB: Oracle-Free Triage of LLM-Generated RTL via Cross-Model Formal Consensus Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21962 - Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22963 - Robustness Analysis of Agentic AI to Inconsistent and Incomplete Tool Responses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22676 - ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.14681 - Evaluating SAT Solver Metrics as Predictors of Human-Perceived Nonogram Difficulty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23300 - Mode-Dependent Rectification for Stable PPO Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05619 - Physical Agentic AI: An Architecture for Orchestrating a Robot Crew with LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22657 - The Compaction Cliff in Long-Running AI Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22752 - Small Language Model enabled Autonomous agent for Language-Conditioned Cognitive Radar Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11596 - AI-based worker guidance in assembly and disassembly operations using multimodal ego/exo-centric data capture and structured task knowledge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22617 - SkillNet: Create, Evaluate, and Connect AI Skills Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.04448 - ExtrinSplat: Decoupling Geometry and Semantics for Open-Vocabulary Understanding in 3D Gaussian Splatting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.22225 - One-Step Evolution for Long-Time Extrapolation: An Error-Bound-Informed and Prior-Guided Neural Residual Framework for Autonomous PDEs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22026 - RSMeM: Knowledge-Enhanced Memory Evolution for Remote Sensing Agents with Systematic Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24772 - What Process Evaluation of Coding Agents Actually Measures: Action, Task, and Step Are Three Different Levels Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22960 - Beyond Endpoint Gains: A Weight-Delta Audit of Medical Specialization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20768 - Software Frameworks for Explainable AI in Time Series Classification: A Systematic Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21449 - Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21242 - When Persona Simulations Are Informative: Graph-Structured Signals for Pluralistic Opinion Sensing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22438 - Walking on the DARKSIDE Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23370 - Anchoring Bias: A Persistent Fairness Backdoor Attack against MLLMs under Continual Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21577 - Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20316 - BenthicDINO: Physics-Informed Self-Distillation for View-Invariant Side-Scan Sonar Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23215 - Relational Structural Causal Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.14892 - AUDITA: certified auditing and causal attribution of adverse outcomes in autonomous multi-agent systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22160 - Power-Performance Characterization of TinyML Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21646 - Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.19066 - Neural-Symbolic Reasoning over Knowledge Graphs: A Survey from a Query Perspective Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.10390 - EviSafe: Evidence-Grounded Safety Evaluation for Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23313 - LLM4LLM: Bridging Kernel Benchmarks and Real Deployment via Closed-Loop Agentic Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21836 - Deep Contrastive Unlearning for Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.14900 - AdaR: A Framework for Equipping LLMs with Adaptive Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.04617 - PEAfowl: Perception-Enhanced Multi-View Vision-Language-Action for Bimanual Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17885 - ESCRAG-R1: Retrieval-Augmented Reinforcement Learning for Emotional Support Conversation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21925 - Statistical Machine Translation Systems of English-Pnar Language Pair : Some Insights of the Emperical Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23120 - Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15389 - Image-Conditional Diffusion Transformer for Underwater Image Enhancement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.05389 - Is Next-Chunk Reasoning RL Really Better than SFT? Revisiting Training Strategies under no-CoT Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23256 - LLM Evaluation on Unseen Questions: Contextual Multidimensional IRT Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22295 - Breaking the Assumptions: Auditing Input-Side Jailbreak Defenses Against Semantic Attacks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21895 - From Inertia to Objectivity: Improving Deep Research Agents with Noise Isolation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23045 - 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 - Bi-EZP: LLM-Guided Bilevel Program Evolution for Ensemble Zero-Cost Proxy Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21927 - How AI Assistance Affects Human Skill Development: A Study of Learning with Logic Puzzles Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23543 - AI emotional support is better only when chosen, but shifts preferences even when it is not Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23196 - Entity Representation Learning Through Onsite-Offsite Graph for Pinterest Ads Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.02609 - HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21863 - ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14354 - LiteEvent-AE: Lightweight Autoencoder for Event-Based Vision on Low-Latency Energy-Constrained Edge Devices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21764 - What Does CLIP Learn for Regional Geolocalization? Probing Visual Cues and Scene Configuration After Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21761 - Reconciling Consistency-Based Diagnosis with Actual-Causality-Based Explanations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08688 - ConvergeFlow: Language Flow with Provable Convergence to Token Embeddings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23551 - PepLLM: ESM-Guided Llama for Structured Protein-Peptide Binding Interface Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21367 - SLogic: Subgraph-Informed Logical Rule Learning for Knowledge Graph Completion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.00279 - Multi-Task Learning for Non-Canonical Phoneme Recognition via Articulatory Feature Decomposition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22273 - Learning with Boolean threshold functions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17493 - RetroDFM-R: Reasoning-Driven Retrosynthesis Prediction with Large Language Models via Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.17448 - Bringing Generative Learning to Representation Learning: Self-Supervised Transfer Learning as Distribution Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.14424 - Hidden in the Request: Explaining Unethical LLM Compliance through Token Relevance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23264 - A-CPES: A Reference Framework for Agentic AI in Cyber-Physical Energy Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22672 - Variance Driven Exploration: A Provable and Efficient Methodology for Pure Exploration in Highly Stochastic Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21995 - Modalities Should Talk to Each Other: Dual-Stream Multimodal Learning for Long-Horizon Influenza Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23373 - Artificial Empathy: Towards a Framework for Unsupervised Agency Detection and Policy Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23030 - Cross-Subject Generalization in Decoding Perceived Speech from Non-Invasive Brain Recordings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22420 - An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.05882 - GeoRisk-RAG: A Hierarchy-Aware Risk Framework for Improving RAG Reliability through Selective Answering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22634 - MoCo-AIS: A Contrastive Learning Framework for Similarity Computation of Vessel Trajectories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17978 - Seismic Acoustic Impedance Inversion Framework Based on Conditional Latent Generative Diffusion Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.13529 - Complexity Induction: Compositional Generalization via Structured Label Distortion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21464 - Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22852 - Pruned Traffic Trees: Native Semantic Compression with a Protocol-Structured Model Family for Encrypted Traffic Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21874 - Do Spoken Language Models Hear Speech as They Read Text? Bridging Structural Gaps Between Speech and Text Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22908 - Evaluating Inference-Time Defenses Against Package Hallucination in LLM-Generated Code Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22652 - A Cross-Architecture Audit of Direction-Based Inference-Time Defences in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27910 - Telco-GAIA: Bilingual Benchmark for Agents in Telecom Domain Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20510 - Procedural Knowledge Extraction from Industrial Troubleshooting Guides Using Vision Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22754 - MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01063 - Why Does Robustness Reduce Superposition? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22155 - LLM-Specific Utility for Retrieval-Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.11358 - Clinical Graph-JEPA: Predictive Patient-State Knowledge Graphs for Cognitive Decision Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22583 - Towards Safer Social Media Platforms: Scalable and Performant Few-Shot Harmful Content Moderation Using Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.13976 - Multimodal examination answer data with expert-designed Outcome-Based Education rubrics for criterion-level assessment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22346 - Training Proactive and Personalized LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.02208 - Beyond Similarity: Heterogeneous Graph Learning for Multi-Objective Food Substitution in Charitable Food Agencies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21979 - Benchmarking Document Parsers on Mathematical Formula Extraction from PDFs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.09874 - Real-TurnTurk: A Multimodal Turkish Corpus for Turn-Taking Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22071 - VisAdj: Learning Adjacency Matrices from Node-Link Images Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21825 - Selection of Heart Sound Segments for Synchronous Classification of Multi-channel Heart Sounds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21499 - Let Credit Follow Computation: Architecture-Aware Credit Transport for Large Language Model Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21501 - MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.03795 - ClawProBench: Trace-Aware Evaluation of AI Agents with Runtime Coverage and Frozen Workplace-Style Holdouts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22510 - From Association to Causation: Improving Retrieval Precision of Retrieval-Augmented Generation via Causal Relations and an Attention Mechanism Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21702 - Which Algorithms Can Graph Neural Networks Learn? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13106 - Performance of a domain-specific large language model in answering patient questions in psychiatry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22797 - SynEHR: Joint Modeling Inter-visit Temporal Evolution and Intra-visit Clinical Structure for Longitudinal EHR Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21673 - Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17443 - MEMORY Wins All: Indirect Bias Injection Attacks via Social Media Feeds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22061 - More Computational Resources Do Not Ensure Higher Scholarly Impact: Evidence from Leading NLP Conference Papers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21806 - Multi-Winner Voting with Argumentative Ballots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23247 - MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.09924 - Does Rank Still Matter? Position Bias When AI Agents Shop on Our Behalf Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22697 - Towards Comprehensive Basketball Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23435 - Joint Causal Structure and Cluster Discovery Using Variational Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22212 - Lagrange: An Open-Vocabulary, Energy-Based Sparse Framework for Generalized End-to-End Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20274 - Analyzing and Mitigating Cross-Lingual Degradation in Multilingual Medical VQA Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22363 - Spending Scarce Confirmatory PET Measurements: Target-Aligned Validation in A4/LEARN Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22223 - On the Role of Citations in Preference Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21376 - SplitLite: Low-Rank Residual Compression for Split Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23018 - Nova: An End-to-End MLIR Compiler for Deep Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00029 - LLM-Based Selection of Incongruent Verbal and Nonverbal Behavior for Virtual Humans Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22731 - AgentWeave: Routing Before Reasoning for Efficient Function Calling in Tool-Rich Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23078 - From SQL Generation to Tool Selection: A Domain-Oriented Pattern for MCP Servers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22063 - KAN-Robust-Bench: A Benchmark for Evaluating the Robustness of Kolmogorov-Arnold Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21488 - TRACE: Artifact-Robust Statistical Shape Modeling from Imperfect Surface Scans - A Case Study in Craniosynostosis 3D Photography Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22131 - Mamba-based Selective State Space Modeling Improves the Accuracy-Complexity Tradeoff of SmolVLA Vision-Language-Action Experts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21407 - DynaContext: Self-Improving Dynamic Contextualization of Optimized Prompts for Heterogeneous Parameter Extraction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22014 - Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.05216 - FreKoo++: Learning Continuous Spectral Dynamics for Temporal Domain Generalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22224 - Read Less, Solve More: Token-Efficient Sparse Reading for AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22237 - MEMONDEMAND: A Memory Management System for Large-Scale Enterprise Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22141 - Beyond Observed Auxiliary Relations: Environment-Conditioned Modeling for Multi-Behavior Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22920 - Evaluating Large Language Models for automatic analysis of teacher simulations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.20360 - Agent-G$^2$: Gaussian Guidance for Agentic Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23318 - Expected Value Alignment for Generative Reward Modeling in Formal Mathematics Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01160 - LITERARYBIGFIVE: Author-Personalized Text Generation in a Unified Interpretable Space Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23124 - Operational digital twin clinics enable task-based evaluation of embodied AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21416 - Improving O-RADS Risk Stratification from Ultrasound Reports: A Comparative Evaluation of Hybrid versus End-to-End LLM Reasoning Strategies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23061 - Interrupting the Chain: Human Perception of AI-Generated Disinformation Through a Kill Chain Lens Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21389 - Future Querying: Can LLMs Serve as Implicit Medical World Models? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23248 - Determinants of Starting Salaries for Filipino Graduates: An Explainable Machine Learning Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21383 - Right-Sizing LLM-Agent Decomposition in VAT Determination: A Pilot Controlled Sweep Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23395 - Role-Specialized Mixture-of-Agents with Open-Weight LLMs for Clinical Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22176 - Learning from the Test: Self-Referential Differential Testing for Deep RL Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22284 - SlideGen: Collaborative Multimodal Agents for Scientific Slide Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.04529 - Lexical Perturbations Disrupt LLM Reasoning: An Empirical Study of Attention Diversion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22140 - Agentic AI for Safety-critical Multi-drone Systems: Challenges and Opportunities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21444 - Characterizing Necessary Losers to Explain Tournaments Losers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23446 - Wazobia Eval: A Benchmark for Nigerian Pidgin Emotion Understanding, Sarcasm Detection, and Cultural Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21369 - ADMIL: Attention-Distilled Multiple Instance Learning for Selective Foundation Model Inference in Pathology Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22066 - Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23478 - The Imitator Game: Benchmarking Robot Imitative Ability Beyond Action Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22301 - The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23541 - Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21544 - presto: Efficient, Training-free, and Open-world Object Placement via Imaginary Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21543 - Dynamic Multi-Byte Prediction With Hierarchical Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15454 - SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21500 - Multimodal Prompt Learning with Irregular EHRs for Robust Monitoring of Critical Care Patients Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21941 - 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 - RACO: Reliability-Aware Coarse-Goal Optimization for Inspection-Oriented UAV Vision-Language Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22678 - MegaMem: A Retrieval Solution for Ultra-Large Context Windows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22137 - 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 - Model of Models: When Does Emitting a Specialist Beat Attending, Adapting, or Tuning? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21386 - FinixDoc: Rethinking Financial Document Parsing Beyond Saturated Benchmarks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22842 - Designing Benchmarks for Knowledge Work Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23262 - Revisiting Multi-Permutation Equivariance through the Lens of Irreducible Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.06665 - Mission-Aligned Learning-Informed Control of Autonomous Systems: Formulation and Foundations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.04356 - Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00726 - E2S-Pruner: Progressive Two-Stage Evidence Fusion for Visual Token Pruning in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23253 - OriginBlame: Record- and Token-Level Data Provenance for AI Training Datasets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13037 - WildHandBench: A Benchmark for Handwritten Text Understanding that Challenges MLLMs and Humans Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22959 - Pointing-VLA: Typed Spatial Grounding Interfaces for Vision-Language-Action Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23138 - A New Type of Adversarial Examples Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.19347 - POOL: Propagated Uncertainty Over Lookalikes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23086 - RoboShape: Information-Theoretic Point Cloud Representations for Privacy-Aware Robot Perception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21380 - Training Needs Trustworthy Worlds: Verified Synthetic Web Environments for Agent Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21898 - Reviewing Model Collapse and Countermeasures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21366 - Multi-Modal Semantic Expansion with Constrained LLM Reranking for Conversational Music Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23484 - Let the Bullets Fly: Multimodal Fake News Detection with Temporal-Aligned Generative Danmaku Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22832 - Cognitive Profiling of LRMs' Reasoning Traces Using Bloom's Taxonomy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23205 - Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27836 - Jiuge-Tuiqiao: An Interpretable Human-AI System for Classical Chinese Poetry Refinement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23098 - SAS: Segment Anything Small for Ultrasound -- A Non-Generative Data Augmentation Technique for Robust Deep Learning in Ultrasound Imaging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.05916 - Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21415 - RSTGCN: Railway-centric Spatio-Temporal Graph Convolutional Network for Train Delay Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.01262 - When Names Cross Scripts: A Source-Grounded Benchmark for Historical Entity Reconciliation in the Mongol World Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23507 - 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 - Sycophants in the Courtroom: Are LLMs Fragile to Juridical Authority and Evolving Legal Standards? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21409 - InjecMEM: Memory Injection Attack on LLM Agent Memory Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23471 - Disagree to Explore, Agree to Commit: Routing-Guided Test-Time Scaling for Software Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22191 - Cultural Moment Benchmark: Evaluating Video Cultural Reasoning and Grounding in Southeast Asia Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23065 - Reinforcement Learning on Benign Facts Amplifies Leakage of Memorized Private Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21727 - Practical Principles for AI Cost and Compute Accounting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.15873 - HIRA: A Human-in-the-Loop Retrieval-Augmented Cascade for Document Classification in Regulated Industries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21792 - Framework for Grounding Healthcare LLMs in a Causal Knowledge Graph: A Cardiovascular Example Pilot Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15382 - FigmaTrace: Capturing Creative Nuances in Human Figma Design Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21460 - GraphMed-LT: Patient-Specific Graph Memory with Latent Clinical Thought Refinement for Multi-Turn Medical Conversations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.03536 - Constructing Predictive Surgical Path for AI-based Capsulorhexis Skill Transfer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21441 - Improving Auto-Design of Neural PDE Solvers with a Domain-Specific Language Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04384 - Deep Learning-Based Multi-User Communication Design for Dense IoT Networks: Interference-Aware Finite-Blocklength Communication and Preliminary MIMO Extensions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22923 - Text-ADBench: Text Anomaly Detection Benchmark Based on LLM Embeddings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.12295 - How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08051 - Barycentric Fused Gromov-Wasserstein Balancing for Causal Inference under Multiple Treatments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22024 - Adversarial Entropy Inflation Against Gumbel-Based Inference Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23375 - CacheRouter: A Dual-Path Tool Routing Architecture with Cache-Preserving Main-Model Isolation for Long-Tail Tool Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22708 - Hybrid Panels: Toward Human-AI Collaboration in Survey Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22582 - Towards a Densing Law for User Representation Learning at Billion-Scale Capacity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23392 - Discovering Dual-Origin Slow Wind from Solar Orbiter with Self-Supervised Contrastive Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22065 - ExecRubrics: Executable Tool-Augmented Rubrics for Verifiable and Efficient Long-Form Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22559 - Automating Multi-Hop RAG Evaluation via TRIAD: From Context Extraction to Validated Dataset Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21558 - Vibe Coding on Trial: Operating Characteristics of Unanimous LLM Juries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18492 - Radial Compensation: The Inverse Base-Distribution Problem for Chart-Based Generative Models on Riemannian Manifolds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.14056 - Development and Feasibility Evaluation of an Edge AI as Medical Device System for Breast Cancer Multidisciplinary Team Meetings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22108 - MemGuard: Persisting Verifier Signals for LLM-Agent Memory Governance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21867 - OVIBench: Benchmarking Online Video Question Answering under Interruption Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22279 - ECHO: A Cognitively Inspired, Auditable Memory Plane for Long-Horizon Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21755 - 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 - Unlearning Is Not Just Erasing: Temporal Decoupling via Generation Inequality Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23020 - SDoH-Aware Narrative Anchoring Bias in Medical LLMs for Trustworthy Clinical Decision Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22802 - Towards a resource for multilingual lexicons: an MT assisted and human-in-the-loop multilingual parallel corpus with multi-word expression annotation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2011.03783 - Measuring Activation Control in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21664 - Scaling Curriculum Learning For Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22549 - HiMA-MDD: A Hierarchical Multi-Agent Harness for Interpretable Multimodal Depression Detection in Clinical Interviews Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21868 - Register Shifts Break LLM Safety: A Bengali Benchmark with Culturally Grounded Harms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22335 - GIM: Evaluating models via tasks that integrate multiple cognitive domains Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18663 - From Solver Feedback to Faithful Plans: Multi-Role Reinforcement Learning for Symbolic Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21897 - Context as an Environment: Programmatic Context Management for Long-Horizon Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21690 - Retrieval-grounded robot program generation and simulation-based correction via Model Context Protocol Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21417 - The Retriever Should Remember: Experience-Amortized Reranking for Long-Term Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22767 - Scalable quantum simulation of continuous-time generative models via tensor networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21700 - CAI-DLLM: Convergence Aware Inference for Diffusion Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22646 - AI University: An LLM-Powered Learning Assistant for Engineering---A Finite Element Method Case Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.08846 - 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 - A Social Media Analysis of Discourse on the Israel--Palestine Conflict on Telegram Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21385 - Rank Reversal in Multilingual LLM Judges: A Label-Free Double-Centering Calibrator Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22432 - HiFiNet: Hierarchical Fault Identification in Wireless Sensor Networks via Edge-Based Classification and Graph Aggregation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.17537 - TELEVAL: A Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarios Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.18061 - One Request, Multiple Experts: LLM Orchestrates Domain Specific Models via Adaptive Task Routing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.12484 - Effects of Theory of Mind and Prosocial Beliefs on Steering Human-Aligned Behaviors of LLMs in Ultimatum Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.24255 - Proxy reliance in large language model decisions is uncalibrated to predictive evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22887 - LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23058 - XTC: Head-Aware Sampling by Excluding Top Choices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22758 - Quantifying geographic domain shift to decouple the geospatial transferability of human mobility flow generation models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21567 - 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 - SPAR-Hate: An Auditor-Guided Multi-Agent Framework for Bilingual Hate Speech Parsing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22018 - The Multilingual FrameNet Corpus Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23037 - MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.10169 - Bulbul: A Dataset for Dialectal Arabic Speech Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21950 - Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21425 - TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22793 - Learning Implicit Constitutive Laws for Dynamic 3D Gaussian Splatting from Monocular Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22102 - ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.09421 - ChainPrune: Evaluating and Reducing Redundancy in Long Chain-of-Thought Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21860 - NeST: Neighborhood-aware semantic alignment and temporal modulation for LLM based time series forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.04806 - PolyUQuest: Verifiable Structure-Aware Web RAG over Heterogeneous Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08269 - AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23041 - Self-Evolving Scientific Agent Discovers Generalizable Physically-Reasoned Fluid Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08405 - Data-Driven Dynamic Algorithm Dispatch with Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21584 - Sigmoid Attention as a Better Substrate for Learned KV Cache Eviction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23296 - Fairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22820 - SEAM: Shot Entity-Attribute Memory for Consistent Short-Drama Generation at Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22725 - Beyond Verdicts: A Graph-Based Analysis of Human and LLM Reasoning in Scientific Fact-Checking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23047 - Weakly supervised concept Bottleneck Learning for Robust Two stage Object centric visual reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22584 - Multi-Context Fusion Transformer for Pedestrian Crossing Intention Prediction in Urban Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.20011 - Training-Free VLM Personalization via Calibrated Residual Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22263 - A Reproducible, License-Aware Distillation Recipe for CPUDeployable Safety Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21570 - Beyond Success and Failure: Length-Aware Contrastive Learning for GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21830 - First-Principles AI finds crystallization of fractional quantum Hall liquids Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03927 - Architecture as Capability Equalizer for Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21747 - Hypergraph Embedding Indexing for Efficient Dense Vector Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22980 - Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.25098 - iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06064 - Spyre-Accelerated Retrieval-Augmented Generation on IBM LinuxONE: A Cloud-Native Architecture for Secure, High-Throughput Enterprise AI Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21393 - Hints, Critics, and Teachers: Prior Injection for Sparse-Reward RL in Vision-Language Math Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21811 - Compositional Chain-of-Relations for Faithful Knowledge Graph Question Answering with Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22762 - AIREP: A Protocol for Per-Decision Evidence in AI Runtime Governance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21363 - CacheSpec: Finding the Sweet Spot for Small Models in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20507 - AI Watchdog: Agent Interfaces for Detecting and Defending Against Manipulative Dark Patterns in AI Conversations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21841 - Continual Uncertainty Learning for Robust Control of Nonlinear Systems with Multiple Heterogeneous Uncertainties Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17174 - MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23473 - Agentic Scaffolding Amplifies Sycophantic Behavior in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21377 - GSAR: Goal-State-Anchor Rewards for Mobile GUI Agents with Self-Evolving Data Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22847 - Redteaming Leading Arabic LLMs with ASAS Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21985 - Where Cognition Lives: Dissecting Emergent from Computed Function in a Minimal Complete Cognitive Architecture Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22347 - Credal Large Language Models for Semantic Commitment under Uncertainty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23244 - Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08169 - Pre-Decoding Acoustic Triage for Budgeted Vision-Language Captioning of Untrimmed Egocentric Video Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22359 - Mitigating Sample-Level Imbalance via Probabilistic Separation for Adaptive Multimodal Fusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.21797 - More Accurate or More Efficient? Evaluating Locally Deployed Compact Open-Weight Language Models for Mathematical Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22048 - EG-ARSA: An Expert-Grounded Open Model for Visual Road Safety Auditing in Low-Resource Settings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23563 - GuardianBench: A Same-Scene Instruction-Contrastive Benchmark for Latent Contextual Risk in Embodied AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21928 - Prime Agent: A Self-Improving RLM Harness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23552 - CogniFold: Always-On Proactive Memory via Cognitive Folding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13438 - Minimal Local Simulation Foundations for LLM- and VLM-Driven Agents in 2D and 3D Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22833 - 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 - When Does AI for PDEs Yield Scientific Evidence? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22504 - Enrich-Retrieve-Rank: Scaling Capability Discovery Beyond In-Context Routing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22695 - K-Bench: measuring model performance on real scientific agent requests Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21601 - Memory-Enhanced Neural Solvers for Routing Problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.16424 - AI Surrogate Modeling for Real-Time Tokamak Equilibrium Prediction: Benchmarking Neural Architectures and Validation on EXL-50U Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23217 - LLMs are Few-Shot Decision-Makers: Generalized Context-Aware Microgrid Frequency Control through Prompt Decision Transformer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21858 - Measuring Stability and Failure Behavior in Language Models Under Structured Perturbations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22138 - CDEG: Learning Decision-Critical Evidence for Long-Horizon Diagnostic Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22899 - Aggregation-Aware Synthetic Text Generation Against Authorship Re-Identification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22161 - Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.18646 - STAGE: Stateful Translation to Agentic Graph Execution with Policy-Scoped Context and Deterministic Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22538 - Triplet2Track: A Hierarchical System with Object-Centric Representations for Reliable Long-Horizon Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22800 - Decision-Support and Modeling with Large Language Models for Geothermal Well Arrays Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22068 - HaReCAP: Habitual-action Grounding for Recursive Large Language Model Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16447 - Adaptive Item-based Collaborative Structures via Noise Rescheduling in Diffusion for Generative Recommendation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23400 - AI Learning and Conceptual Transfer in the Game of Hidden Rules Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21372 - DiagFlowBench: Evaluating How Language Models Handle Off-Procedure Inputs in Grounded Diagnostic Dialogue Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17904 - Agentic Security: A Systematization of Tools, Failure Modes, and Design Laws for LLM-Driven Penetration Testing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21423 - Meta-Ctrl: Guaranteed Plan Generation by Decoupling Syntactic and Semantic Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22149 - The Greatness of Science Cannot Be Planned: Agentic Auto-Research is Fuzz Testing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09855 - Towards Zero-Shot Task Transfer with Neurosymbolic World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17959 - Don't Repeat Yourself: Stopping Verbatim Loops at Sampling Time Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22761 - Geo-VLA: Geometry-Aware Vision-Language-Action Planning via Internalization of Map Semantics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21440 - Shaping the Evolutionary Dynamics of Robot Morphology via Adaptive Control Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23100 - There Is No Neutral Harness: Modern LLM Leaderboards Are Manufactured by Config-Fragile Items Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21382 - MACD: Multi-Agent Clinical Diagnosis with Self-Learned Knowledge for LLM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.20067 - Improving Energy Efficiency of Oil Platforms Through Optimal Loading of Diesel Generators Using Machine Learning and Search Algorithms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22076 - AutoResearch: Insight In, Hallucination Out Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17906 - When Entropy Is Not Enough: Reclaiming Lost Semantics in LLM Output Length Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15592 - Search Broadly, Seek Evidence on Both Sides, Decide Narrowly: Evidence-Admissible GraphRAG for Longitudinal Clinical Event Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22062 - Evaluating the Efficacy of LLMs to Emulate Realistic Human Personalities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.14879 - Jagged Judges: Epistemic Stability Under Perturbation, Pressure, and Persistence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12645 - GAN-Diff : Coupling Pretrained WGAN-GP Features with Conditional Diffusion U-Nets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22272 - KVBoost: Chunk-Level Key-Value Cache Reuse with Deviation-Guided Recomputation for Efficient Large Language Model Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21362 - What You Can't See Is What You Learn: Restricted Evidence Visibility Favors Compositional Generalization in Shared-Genome Language-Model Societies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20054 - DF-MoE: Generalizable Deepfake Detection via Multimodal Sparse Mixture-of-Experts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23363 - Hack-Verifiable Terminal Bench: Evaluating Reward Hacking in Terminal Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22103 - Semantic Substrate Dynamics Theory: An Operator-Theoretic Framework for Geometric Semantic Drift Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18699 - SchemaRouter: Field-Aware Tool Routing for Efficient Heterogeneous Agentic RAG Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21375 - InfraBench: Evaluating Infrastructure Agents Across Layers, Lifecycle, and Risk Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11234 - EMPIRE: Explicit Manipulation Planning as a Learnable Intermediate Representation for Egocentric Hand-Motion Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22449 - VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13880 - ChebBooster: A Training-Free Approach for Efficient Diffusion Transformer Inference via Chebyshev-Inspired Extrapolation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23429 - Robust Lightweight Deep Learning Models for Oral Cancer Screening Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21583 - ReWorld: An Interactive World Model with Long-Horizon Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23565 - NL2SHACL-Bench: A Benchmark Suite for Natural Language to SHACL Translation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07530 - Closed-loop AI achieves certifiable engineering design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21976 - Clarify User Expertise: Towards Proactive Conversational Agents Tailoring Responses to User Proficiency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22266 - Concepts for Securing Agentic AI Coding and the Terok Environment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22930 - Do Not Copy/Paste: Soft Barriers for Copying in AI-Assisted Programming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22638 - MCP-Universe RL: A Framework for Training MCP Tool-Use Agents via Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22167 - 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 - Mycelial Search: A Graph-Structured Metaheuristic for Continuous Optimisation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23323 - Read, Write, Relax: Why Neural PDE Surrogates Need Both Global and Local Processing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21677 - Correcting Variable Importance Scored by Random Forests Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10770 - The Measurement Revolution? Credible Measurement and Inference in the Age of AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23524 - Evaluation of Small Vision-Language Models on Qualitative Mechanical Problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22143 - MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00708 - SAFE-G: Structure-aware Faithful Evidence-guided Generation for Knowledge-based Visual Question Answering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21796 - TEE-X: TEE-aware Acceleration Framework for Large Vision Models at the Edge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22716 - A Physical Response-and-Memory Model for Muon Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22994 - Think Only When Needed: Prompt-Authority Control for Selective Slow-Path Intervention in Vision-Language-Action Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23224 - On Predicting Vulnerability Severity Using In-Context Learning: An Industrial Case Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22089 - Small Reasoning Models are Instruction Followers in Function Calling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22472 - Reward-Free Continual Adaptation for Resilient Space Robots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23452 - Budget-Constrained Embodied Perception: Four Resource Walls and a Pre-Registered Evaluation of Access-Structured Perception on Open Models at less than 31B Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22975 - Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23497 - ODG-NoMaD: Overhead-Camera Direction-Guided NoMaD Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21395 - Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22642 - Automated Construction of FAIR Digital Object Knowledge Graphs from Flat Cultural Heritage Records Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23263 - Evidence-Aware MapReduce for Forkable Compute Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09689 - Coalition-Aware Skill Reliability for Self-Evolving Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22610 - ReasonEdit: Editing Vision-Language Models using Human Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02408 - A Survey on Human-AI Collaboration with Large Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2403.04931 - WAM-OPD: On-Policy Distillation for World Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22364 - Lexical Coupling in GUI Element Grounding: Sentence Embeddings Track Labels across Mobile and Web Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21794 - Adapter-Based Few-Shot Continual Learning for Malicious Packet Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23536 - From Mastery Profile to Simulated Response: Stochastic Student Knowledge Graphs (SSKG) for Faithful LLM Student Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21668 - BioMed-Agent-RL: A Meta Learning, All You Need for Biomedical Applications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21864 - Improving Few-Step Language Flows with Untied Self-Conditioning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22244 - GameXpert-Bench: How Far Are Coding Agents from Expert Game Development? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21833 - Where World Models Break: Natural-Input Failure Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22421 - SkillEffect: Checked Lowering for Memory-Bounded Agent Tools Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17007 - What Proves You Wrong: Benchmarking Language Models on Falsifiable Research Ideation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22948 - Dissecting Neuro-Symbolic Quality Assurance for Synthetic Oncology Data Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22085 - TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22788 - 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 - Beyond the Harness: End-to-End Optimization of Context Artifacts for Enterprise Text-to-SQL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22830 - PatchWrite: One Line, Not One Section -- Compile-Gated, Validity-Preserving Editing for AI-Drafted Manuscripts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23001 - PsychJail: Exploring Psychological Jailbreaks via Multi-Turn Persuasion of LLM Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23028 - Self-Supervised Graph Representation Learning for In-The-Wild Wearable and Smartphone based Emotion Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22387 - ProBel: Propaganda Detection with Techniques, Spans, and Explanations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22388 - Hyperbolic Hierarchical Clustering for Visual Representation Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22665 - Query-Driven Multimodal Information Extraction from Long Documents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22214 - Benchmarking Retrieval-Augmented Generation Strategies for Large Language Model-Based Travel Mode Choice Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.17527 - FinSTaR: Towards Financial Reasoning with Time Series Reasoning Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.03460 - EarthVerse: Benchmarking Scientific Agents Across Dynamic Earth Systems and Natural Hazards Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23525 - PatchGate: Narrowing the Verbalization Gap with Intrinsic Object Inventories in Frozen Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21819 - Teaching LLMs How ICU Physicians Approach Clinical Reasoning Through OMOP-Aligned Retrieval Improves Reasoning Across Clinical Domains Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22622 - GenCoord: Skill-Path Commitments under Private Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22055 - What is mathematics now, and what should it be? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23218 - SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23564 - Beyond Benchmarking: Scenario-Based Evaluation of Large Language Models for Personalized Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.05346 - Hierarchy-Aware Supervised Uncertainty Estimation for Black-box LLM Taxonomic Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22839 - Why This, Not That? Mining User Profiles for Pair-wise Counterfactuals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21662 - HERO: Human-profile Enhanced Retrieval Optimization Framework for Long-term Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22310 - Toward Effective and Reliable LLM Agents via Dynamic Ontology Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22974 - Safety Hacking in Constrained Best-of-$N$ Inference-time Scaling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22915 - Consistency Is Not Coherence: Orientation Search for Certified Alignments Between 4D Defence Upper Ontologies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21914 - HANSARD: A Reference Architecture for Forensic Readiness, Runtime Witnessing, and Graded Attribution in Autonomous Multi-Agent AI Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22512 - Inferring Action from Future Latent State for Robotic Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22067 - Functional compatibility as a determinant of persistent neural learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22462 - ExplainGuard: A Zero Trust Framework for Post-Hoc Explanation Integrity Guarantees in Blackbox XAI Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21803 - LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16890 - Generate in the Chart, Not on the Boundary: Function-Symbol Grounding for Hard Constraints in LTN-GANs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21605 - The Abstention Protocol: RCA for Clos Fabrics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21412 - Triangular Fuzzy Rescaling Distance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19234 - GuardPaint:SpeculativeSafetyDecodingforText-to-ImageGeneration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21869 - Reliability- and Anatomy-Consistency-Aware Multimodal Learning for Robust Fracture Classification from Bangladeshi Radiographs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21482 - Retrieval-Augmented Classification of Environmental Mitigations in Hydropower Licensing Documents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23241 - CRS-Bench: A Reference-Relative Reliability Benchmark for Medical Image Encoders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22059 - Hate Speech Classification In Roman Urdu: A Comparative Study On Parameter Efficient Fine-Tuning And Prompt Engineering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21408 - Vision-Language Models for Occupational Physical Exposure Assessment: Estimating External Hand Forces in Manual Material Handling Tasks from RGB Video Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22586 - TessIndex: Capability Verified Identity System for the Agent Economy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21942 - CMI-Mem: Toward Generalizable Long-Term Memory Management via CMI-Augmented Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20553 - A Scalable Vector Graphics Latent Space Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21893 - Semantic Compression Trees: Multi-Resolution Knowledge Retrieval via Hierarchical Semantic Residuals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21610 - Hierarchical Compositionality for An Assistive AI Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10330 - ATHENA: Knowledge-guided agentic neural architecture search for AutoFormer-based electronic health record modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21712 - Multi-Agent Discovery and Resource-Aware Autonomous Exploration of Scientific Datasets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22045 - MOCLIP: A Foundation Model for Large-Scale Nanophotonic Inverse Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.18980 - Semantic Reasoning Denoising: Correcting Language Model Reasoning with Semantic Operators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22090 - Enhanced Artificial Neural Networks Using QHAdamW in Air Quality Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21463 - DeepSAGE: Stage-Aware Reinforcement Learning for Structured CBT Counseling Dialogue Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22615 - HiViS: Hiding Visual Tokens from the Drafter for Speculative Decoding in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.23928 - Addressing the Selection Problem in Explainable AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22356 - SkillAlchemy: Open-World Agent Skill Creation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23417 - Beyond Two Bytes per Letter: Tokenization Overhead in Cyrillic AI Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21384 - Composable Trust Infrastructure for Manufacturing Knowledge Graphs: Cross-System Provenance, Temporal Reasoning, and Decision Traceability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21418 - Evaluating Multimodal Narrative Understanding of Popular Hollywood Films Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21430 - SRMT: Shared Memory for Multi-agent Lifelong Pathfinding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.13200 - Scaling Laws for Task-Specific LLM Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24747 - TASSO: TAsk-Specific Subspace Optimization for Continual Learning of Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21487 - AraDetox: A Multi-Dialect Arabic Detoxification Dataset Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22894 - Coarse Indexing, Fine Evidence: Decoupling Temporal Granularity in Long-Video RAG Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23011 - What is an intelligent system? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2009.09083 - BLADE: Bilevel Low-rank Augmented-Lagrangian Erasure for LLM Unlearning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22557 - Why we need an AI-resilient society- Profiling Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/1912.08786 - From Isolation to Alignment: Unified LoRA for Efficient Multi-Task Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.05078 - Repo2Skill-Evo: Repository Skills Go Stale in Silence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21964 - The Emergence of Relevance Through Axiomatic Attention Patterns During LoRA Fine-Tuning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23338 - CyrillicQA: The Influence of Phonetically Encoded Secret Language on LLM Performance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21462 - Physics-Knowledge-Guided Hybrid Neural Learning for Arctic Sea Ice Concentration Evolution and Short-Range Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21767 - LSem2Vec: A Simple yet Effective Two-Stage Approach for Source Code Embedding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2409.14644 - CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23181 - Training a Knowledge Base: Supervised Structure Learning for Agent-Curated Document Stores Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21829 - Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23391 - Beyond What Meets the Eye: Unveiling Situational Illusions for Multimodal Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22232 - Robustness of IR Models to Collection Growth Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23419 - LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23200 - Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23311 - ConstructCIE: A Dataset for Extracting Causal Information from Construction Accident Narratives Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06495 - A Comprehensive Analysis of Arabic Natural Language Processing Research: Trends, Topic Evolution, and Research Gaps -- A Bibliometric and Topic-Based Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23421 - How to Train a Critic Stably and Efficiently Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23566 - Expectations and Practices around AI Disclosure in CS Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23271 - What's the Catch? Evaluating Temporal Consistency in Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23474 - Better Retrieval, Worse Robustness:How Multi-hop RAG Amplifies Upstream ASR Errors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22872 - Counter with Evidence! A Multi-Agent Memory Efficient Reasoning Framework for Hate Category Informed Counterspeech Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23152 - Molecular LLM Agents: From Architectural Design to Scientific Autonomy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23104 - Apodex 1.1: Scaling Agentic Intelligence for Complex Work Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23283 - RIG-RoPE: Relation-Stratified Multimodal Attention with Instance-Local Rotary Geometry and Representation-Aware Traversal Coordinates Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05154 - Most of the LLM routing gap is task type Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23023 - A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.20073 - Dual-Cache Latent Space Communication between Heterogeneous Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20617 - Mint-Agent: Introducing Finance-Native Agentic Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16386 - Structure is information: structural identifiability mappings for machine learning with partially observed dynamical systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.04131 - Learning Prostate Anatomy at Test Time for Cancer Detection in Micro-Ultrasound Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20557 - Exact and general decoupled solutions of the LMC Multitask Gaussian Process model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2310.12032 - FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21096 - BF1: A Causal Dyadic Sparse-Attention Retrofit for Efficient Long-Context Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20427 - PSK at WMT 2026 MIST: Task-Specialized QLoRA Adapters for Multilingual Summarization and Question Answering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20757 - 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 - C-Score: Beyond Accuracy for Robustness Assessment in Semi-Supervised Learning under Open-World Unlabeled Contamination Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20667 - RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24817 - BIPPO: Budget-Aware Independent PPO for Energy-Efficient Federated Learning Services Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.08142 - Predicting Resource Efficient Hamiltonian Decomposition for Continuous-Time Quantum Walk Simulations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20660 - Llama-Mobile: Efficient 2.7-Bit Quantization of VLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21134 - TracingFlow: A Simulation-Free Trajectory Inference Framework Based on Second-Order Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21070 - SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03092 - Across-Design Uncertainty in Short Pricing Panels: Evidence from Simulated Price Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21334 - From Thermal Preference Prediction to Adaptive Thermal Intervention: A Reinforcement Learning Approach Using Physiological and Environmental Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20423 - RODE: A Radial-Orthogonal Decoupled Engine for Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21024 - Rigorous Evaluation of Large Language Models for Malaria Drug Discovery: Trade-offs in Performance, Scale, and Resource Utility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20418 - In-Cell Learning: Deployed Language Models Can Learn New Knowledge Without Changing a Single Stored Bit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20873 - On Finite-sample Concentration of Median of Incomplete U-Statistics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00661 - BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21137 - PerturbRx: Learning Treatment-Conditioned Latent Transitions for Patient Drug Response Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21349 - JuryProbe: An Empirical Consensus-Risk Diagnostic for Routing Reference-Free Factuality Judge Panels to Grounded Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20607 - Attributing Preprocessing Invariance in Spectral Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14227 - The Exceedance Design Effect: Effective Sample Size for Thresholds under Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21262 - Towards Truly Unsupervised Evaluation of Feature Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12057 - Multilingual Verifier Bias in RLVR: Benchmark, Rollout Diagnosis, and the Cross-Lingual Selection Bottleneck Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20362 - TriPLU: Bypassing the Gate with Direct Trilinear Product FFNs in Tiny Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20360 - Perseus: Interactive Time Series Segmentation with Sparse Supervision via Stateful Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.09930 - Primal Acceleration of Newton's Method Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21359 - Defining Decentralization: An Ontological Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09748 - Learning Exact NVIDIA SASS Encoders with $\mathbb{F}_2$ Linear Algebra Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20532 - TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21343 - No PUN Intended: Plausible Unknown Names for Person-Centred LLM Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21206 - Reinforcement Learning for Continuous-Time Jump Markov Decision Processes with Applications to Network Dynamic Pricing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20680 - Deterministic and probabilistic neural surrogates of global hybrid-Vlasov simulations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.12614 - Sharing the Control Authority Between Deep Reinforcement Learning and Model Predictive Control: Application to Multi-Class Transportation Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20858 - Designing a Robust LLM-Based Evaluation System for Agentic AI in Drug Discovery Through Human Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21057 - From a Static Multi-Level Small Semantic Codebook to a Dynamic Single-Level Large Semantic Codebook for Generative Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21012 - Machine Learning and ARIMA Model Averaging for Adaptive Public Health Forecasting: Comparative Evaluation and an Ontario COVID-19 Case Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20406 - FlavourBench: Ranking Frontier Language Models with Executable Culinary Ground Truth Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20574 - FeLoG: Scalable and Efficient Distributed Graph Embedding with Feedback Loop Mechanism Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22180 - ReCurveflow: A Flow Matching Framework that Learns Curved Reaction Trajectories to Predict Transition State Geometries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20869 - Amplifying the imaging power of digital sky surveys with space telescopes data and generative AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20666 - Truthful Calibration Measures for Sequential Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21348 - Learning Minimal-Deviation Corrections for Multi-Dimensional Mismodelling in HEP Simulations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07460 - INFUSER: Influence-Guided Self-Evolution Improves Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09052 - Interpretable Information-Decomposed Brain Graph Learning for fMRI-based Disease Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20380 - A Deep Reinforcement Learning Framework for Closed-loop Guidance of Fish Schools via Virtual Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28200 - TreeWY: Speculative Verification for Gated DeltaNet Hybrids Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20961 - GRALIS: Fusing Coalition and Gradient Attribution with Closed-Form Conservation Error and Finite-Sample Guarantees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05480 - SEISMO: Explanation-Aware, Trajectory-Conditioned LLM Agents for Sample-Efficient Molecular Optimisation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00663 - Advanced Linear Algebra with Applications - Part I (Numerical linear algebra for PDEs, machine learning, and data assimilation) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21234 - When Clean Data Hurts: Learning with Monotone Corruptions Beyond Binary Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20480 - If It Walks Like an Arbitrage: Protocol-Agnostic Detection with Decidable Structural Equivalence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20377 - CDRL: Certification-Driven Reinforcement Learning for Neutrino Flavor Model Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20686 - Uncertainty-aware Multi-fidelity Closure via Conditional Normalizing Flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09857 - The Dual Nature of LLM Persona: Aggregated Tendencies and Frame-Dependent Geometry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.02368 - VA-DPO: Valence-Arousal Direct Preference Optimization for Controllable Emotion Generation in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20374 - Keep Your Friends Close, and the Right Neighbours Closer: Disaster-Conditioned Kernel-Regularized Graph Attention for Building Damage Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20548 - Efficient Inference for Inverse Reinforcement Learning and Dynamic Discrete Choice Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.24407 - Latent Softmax for Data-Efficient Phoneme-Based Multilingual ASR Across Tonal and Non-Tonal Languages Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01281 - Bankruptcy Prediction via Hybrid Resampling and Stacking Ensemble Techniques with Explainable Artificial Intelligence (XAI)-Driven Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20343 - Resolution-Consistent Greedy Neural Approximation on Infinite-Dimensional Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20812 - Shared Physics Responses Recover Hidden Rankings in Neural Operator Libraries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20441 - Beyond Imitation: Self-Improving Robot Policies via Off-Policy Q-Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21204 - Harmonic Torsional Diffusion for Protein-Ligand Flexible Docking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20366 - 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 - World models of environment, agent and joint agent-environment systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20401 - ELVAE: Evidential Learning-Based Variational Autoencoder for Uncertainty-Aware Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10398 - Explaining Intrinsic Moral Self-Correction with Mechanistic Interpretability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.11924 - Non-Shattering at and Above the Dynamical Temperature in the Spherical Pure p-Spin Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14369 - Interpretable clustering via optimal multi-way decision trees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13586 - Capturing Cardiac Cyclicity through Phase-Equivariant Self-Supervised Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21147 - Keyed Provenance Watermarking with Complementary Lattice-Based Secure Aggregation for Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20580 - Stored in Optimizer State, Valued by Later Training: A Causal Account of Subliminal Trait Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20442 - When Retrieval Fails Before It Begins: Structurally Indirect Prerequisite Eviction as a Retention Failure in Agentic Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20400 - EviRank: Structured Relevance Evidence for Multimodal Image Re-ranking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20886 - An Introduction to Bayesian and Frequentist Simulation-Based Inference with Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21702 - Approximate Homomorphisms and Convergent Representations in Transducers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20428 - Decision Tree and K-Means Analysis of Raman Spectra for Edible Oils: A Physics-Informed AI Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20440 - Lightweight Adaptive ReduNet via Hyperspherical Manifold Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20668 - Smart Exploration in Reinforcement Learning using Bounded Uncertainty Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.05978 - The Metanym Game: An LLM Benchmark Without Ground Truth That Rises With the Models It Measures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21008 - Minimax Optimality of Score-Entropy Discrete Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20635 - NeuroStrata: An Electroencephalographic Connectivity-Aware Deep Representation Learning Framework for Dynamic Brain Network Analysis of Mental Stress Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20354 - Query Efficient Structured Matrix Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.19290 - Rethinking Expressivity and Efficiency in Test-Time Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21308 - Mutual information and sensitivity analysis for feature selection in customer targeting: a comparative study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20447 - Curriculum-Aware Interpolate-then-Refine: Learned Physiological Time-Series Imputation under Realistic Missingness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21207 - Meta-clustering of milk mid-infrared spectra identifies dairy cow groups associated with negative energy balance in early lactation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20653 - Robust Discovery of Coarse-Grained Continuum Equations from Microscopic Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20404 - When Graph-JEPA Learns the Wrong Thing: Diagnosing and Repairing Category-Conditional Collapse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20516 - Behavior-Consistent Deep Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21214 - What a World Model Represents Is Three Questions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.06640 - Consistency Models for Fast MRI Reconstruction Using Regularization by Denoising Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20561 - Temporal Validity on Real Software Histories: Eliminating Stale-Fact Errors in Code-Assistant Memory over GitHub Fixes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20685 - Jacobian-guided Noise Injection for Quantization Robustness in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20988 - LTR-ICD: A Ranking-Aware Framework for Automatic ICD Coding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.13922 - Separating Covariate Shift from Mechanism Change with Two Discriminators: CJSD, a Conditional Discrepancy with an Exact Covariate-Concept Decomposition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19885 - Doctor Rashomon and the UNIVERSE of Madness: Variable Importance with Unobserved Confounding and the Rashomon Effect Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.12734 - On the Within-class Variation Issue in Alzheimer's Disease Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2409.16322 - Training, learning and inference: unified dynamics of neural systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20965 - CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20803 - Degree-Mass Message Passing for Betweenness Ranking in Directed and Undirected Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09716 - Generalization Measures under Controlled Covariate Shift: A Regime-Aware Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01718 - ConceptTS: LLM-Guided Concept Bottlenecks for Interpretable Multivariate Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21277 - Exploratory As-Analyzed No-Detection of Culturally-Marked Predicate-Triggered PII Amplification in a Synthetic-English RAG Probe: A Predicate-Resource-Confounded Audit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20351 - Metag: A dataset to build agentic meta-reviewing capabilities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20488 - Rethinking Demonstration Unlearning in Imitation Learning for Robotics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20784 - TRACE-C: Rank-Calibrated Relational Anomaly Detection for Multi-Stream Operational Telemetry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21251 - Automatic classification pipeline for glitches in the Virgo detector Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13687 - Optimistic Online LQR via Intrinsic Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28938 - Benchmarking noisy label detection methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.16211 - Decoupling Policy Extraction for Offline Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20909 - Investigating Target Class Influence on Neural Network Compressibility for Energy-Autonomous Avian Monitoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.17751 - aiXamine: Unified Black-Box Evaluation of Cross-Dimensional Trade-offs in LLM Safety, Security, and Privacy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20554 - STS: Efficient Sparse Attention with Speculative Token Sparsity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15508 - Regression-Based Estimation of Causal Effects in the Presence of Selection Bias and Confounding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.20546 - Uncertainty propagation in auto-regressive random neural network models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20483 - HIP: Hessian Interatomic Potentials without derivatives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.21624 - Maximum Likelihood Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02710 - Personalized Privacy Control in LLMs via Attention Head Intervention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21209 - Faults That Fortify: CNN Adversarial Robustness via GPU Undervolting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20572 - SAC-Copula: Quality-Preserving Watermarking for Diffusion Language Models via Smooth Correlated Gumbel Fields Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20839 - Valid Inference with Synthetic Data via Task Exchangeability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13629 - CFM: Language-aligned Concept Foundation Model for Vision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13798 - TH-GNN: Heterogeneous Temporal Graph Neural Networks for LLM-Agent Shilling Attack Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20376 - Federated and differentially private estimation of KL divergence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.16478 - MIL-BERT: Classification of Arbitrarily Large Text with Performance and Explanatory Guarantees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20636 - Spatially Aware Dictionary-Free Koopman Eigenfunction Identification for Modeling and Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.22648 - Adaptive Inference for Resource-Constrained Dynamic Pricing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03736 - When Does Forecasting Reveal Temporal Structure? A Stability Analysis of Time-Series Structural Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10433 - AudioWorldSim: Realistic Binaural Audio Datasets For World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21075 - Infinite-dimensional generative diffusions via Doob's h-transform Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06621 - Scaling Muon for Diffusion Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20818 - DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.10375 - GEO-Flag: Detecting and Measuring GEO-Optimized Web Content Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16824 - Geometric Regularization for Long-Tailed Semi-Supervised Learning via Gaussian Feature Bridges Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20710 - CPC-CMS: Cognitive Pairwise Comparison Classification Model Selection Framework for Document-level Sentiment Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.14022 - Compared to What? Baselines and Metrics for Counterfactual Prompting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.01048 - On the Transferability of Agricultural Weed Detection Under Cross-Field Distribution Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21254 - Asymmetric Capacity Allocation in Self-Refinement Pipelines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21345 - A continually expandable foundation model for brain MRI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08319 - COEC: Calibrated Orthogonal-Equivalence Compensation for Structured Pruning of Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21142 - The Fast Mixing Mechanism for Differential Privacy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30600 - GroupSegment-SHAP: Shapley Value Explanations with Group-Segment Players for Multivariate Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.06114 - Thermo-FL: Thermal-Aware Robust Federated Fine-Tuning of Large Language Models for Edge AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21172 - Tydra: An Efficient Hybrid Model for Tabular Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21199 - Fuzzy-MoE: Interpretable Regime-Conditioned Expert Routing for Non-Stationary Multivariate Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20761 - Event-triggered Implicit Perturbation for Zeroth-Order Fine-Tuning of Spiking Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21223 - Towards Automated Discovery: A Review of Generative Models, Multimodal Learning and Closed-Loop Workflows in Inverse Materials Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02507 - Wrong-Physics Backdoors in Neural PDE Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20439 - An Automated Pipeline for Few-Shot Bird Call Classification: A Case Study with the Tooth-Billed Pigeon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.16276 - PROBE-Web: An Interactive System for Probing Evaluation Landscapes of Knowledge Graph Completion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08926 - Efficient Exploration at Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.17378 - A Neurosymbolic Approach for Constructing Planning Domain Models from Clinical Narratives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21186 - AgentDecarbonizer: Carbon-Aware Execution for AI Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20566 - Interpretability in Deep Time Series Models Demands Semantic Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02239 - Fine-tuning LLMs for Tourist Trajectory Prediction using Field Experiment Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20830 - Human-JEPA: A Human-Centric Vision Model that Perceives and Anticipates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21160 - Bern2Edge: A Neurosymbolic Compiler for Edge Deployment via Bernstein Polynomial Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20497 - COMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21030 - Calibrate-Then-Delegate: Safety Monitoring with Risk and Budget Guarantees via Model Cascades Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14251 - Actively Learning Joint Contours of Multiple Computer Experiments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.13530 - Information Geometry of Message Passing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15922 - AgentOCR: Reimagining Agent History via Optical Self-Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.04786 - Free-Probability Kernels for Zero-Rollout Hyperparameter Selection in Reservoir Computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20998 - Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01444 - Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17310 - RiskTraf: Risk-Extrapolated Residual Learning for Multi-Variate Traffic Flow Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20656 - Amortized Bandwidth Learning for Kernel Density Estimation under Logarithmic Score Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20445 - Provable Edge-of-Stability for Adam on a One-Dimensional Quadratic Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20638 - When to Ponder: Adaptive Compute Allocation for Code Generation via Test-Time Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.00894 - Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05040 - MeltwaterBench: Deep learning for spatiotemporal downscaling of surface meltwater Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.12142 - A Critical Audit of Spatiotemporal Forecasting Benchmark Datasets and Baselines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20980 - AutoOR: Scalably Post-training LLMs to Autoformulate Operations Research Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16804 - SPD Matrix Learning for Neuroimaging Analysis: Perspectives, Methods, and Challenges Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.18882 - The Intrinsic Dimension of Prompts in Internal Representations of Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.10573 - Green BOA: Determining the environmental break-even point for ML-based data compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19994 - Neuro-Geospatial Modelling of EEG Affective States Using Literature-Informed Environmental Context Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20807 - Detecting Functional Memorization in Code Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12764 - Causal Modeling of Adverse Pregnancy Outcomes via Adaptive LLM Proposals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21079 - Reinforcing Multi-Turn Reasoning in LLM Agents via Fine-Grained Reward Structure and Credit Assignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.11821 - SPARCL: Spectral Partitioned Analytic Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21307 - Hidden Axis of Uncertainty: Latent-Posterior Alignment in Graph Neural Networks with Bayesian Output Layers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20758 - Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20953 - Conditional-Independence-Regularized Distributional Autoencoders for Mixed-Type Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20562 - Training DeepFilterNet with Accurate Room Acoustic Simulations Improves Single-Channel Speech Enhancement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20971 - Forecasting with an N-dimensional Langevin Equation and a Neural-Ordinary Differential Equation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.07359 - Time-Aware Tranformer-Based Prediction Model for AECOPD Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21324 - RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.01913 ## Community - EVE Online: The Move to Python 3 Begins! Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Aug/25/eve-online-move-to-python-3/