06:00LLM Monitor Validity Failures: Security Evidence Path IssuesResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Improving Generative Policies from Observational DataResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00ScoutRoute: Efficient MoE Routing via Internal Model SignalsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00S-GAP: Stealthy Attacks on GraphLLMs via Unified PrimitivesResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Evaluating Narrative-Induced Sycophancy in Large Language ModelsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00GEMS: Molecular Structure Identification via Guided Search over Isomer GraphsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00OwlSight: A Chain-of-Thought Reasoning MonitorResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00A new framework to model mental states and their evolutionResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00FuTransformer: FP8 prefill and INT4 decode for Llama-style inference on Hopper GPUsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Consistent Concept Discovery with Sparse Coding Beyond SAEsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Self-building labs speed up scientific researchResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00AI agents for automating reproducibility in medical researchResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00CausalEvo: Causal Skill Self-Evolution for Health LLM AgentsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Can LLMs effectively calibrate engineering simulators under budget constraints?Research & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Interactive clarification to improve Lean formal specificationsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Generative agents for real-aligned urban mobility simulationsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Evaluating explainable harmonic decision-making on music corporaResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00M2CG: A Non-Recursive Approach for Medical Image AlignmentResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00LLM Safety Evaluation: A Bias Linked to Query FormResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00TRACE: Efficient Transformer Residual Activation Encoding for Distributed Edge InferenceResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement FormalizationResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00New model for multi-channel time series forecasting using sparse attentionResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00TUPLE-Bench: Evaluating privacy-utility trade-offs in typed decision modelsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Neural Expansion: A Unified Mechanism for Deep Neural Network GeneralizationResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Behavioral Couplings: Unintended Behaviors Emerge in Fine-Tuned LLMsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00New adaptive method for pixel diffusion transformers with MFlowResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00GVPO: A new optimization method for LLM post-trainingResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Survey of Explainable Reinforcement Learning: Methods, Targets and GapsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00CMASE: A multi-agent framework for real-time social intervention modelingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00UniWM: Unified World Models for Visual Navigation with Memory-Augmented PlanningResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10