06:00Plausible explanations mislead multimodal AI judgesResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00ToMStories: Evaluating Theory of Mind in Language ModelsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00New method to measure LLM uncertainty through causal robustnessResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00On-Demand Hard Instances for Algorithm EvaluationResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Diverse Reasoning Paths Matter: Symbolic Equivalence Augmentation for RL ExplorationResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00NoveltyScope: Multi-agent research assistant for novelty assessment of scientific papersResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00ARBOR: Detecting reasoning failures in long chains of thoughtResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00OrderFlowDiT: Diffusion Transformer for Limit-Order Volume ForecastingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00CADENCE: Adaptive decoding method to speed up text generationResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Reducing private data leakage in fine-tuned LLMs via neuron pruningResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00STRIDE: New benchmark for spatiotemporal reasoning in autonomous drivingResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00The Reliance Hypothesis: Chain-of-Thought Faithfulness Rises as Language Resource Level FallsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00AnchorQ: Efficient Policy Improvement for Robotics via Structured Latent Action AnchorsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00New budget allocation method for optimizing LLM tree searchResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00LLM agents in collective-risk dilemmas: limited adaptabilityResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Learning to Be Guided: Optimizing Latent Geometry for Classifier-Free GuidanceResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00RLVR: Are long rollout windows really necessary?Research & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Competence-based evaluation of logical reasoning in large language modelsResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00HAPACT: A benchmark for localizing physical impacts on the human body in videosResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00COMET: Method for Continual Vision-Language LearningResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Same Attention Circuit Drives Multiple Post-Training BiasesResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Aligning Language Models for Counterfactual InvarianceResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00NL2SQL via iterative self-refinement with specialized agentsResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Prism Attention: Efficient KV-Cache Sharing for Long-Context LLM InferenceResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00PersonaCUABench: Evaluating computer-use agents based on user personasResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Noise-robust algorithm for graph data labelingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00SpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural NetworksResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Unifying Embodied Foundation Models via a Model-to-Policy FormulationResearch & Sciencecs.AI updates on arXiv.org9/10Relevance 9 out of 10
06:00Relational models trained on synthetic data for graph databasesResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10
06:00Local proxies for memory-efficient neural trainingResearch & Sciencecs.AI updates on arXiv.org8/10Relevance 8 out of 10