๐Ÿ“„ New Papers

TitleCategoryScoreLink
Optimizing Neurorobot Policy under Limited Demonstration Data through Preference Regretcs.AI0Open
Structural Rigidity and the 57-Token Predictive Window: A Physical Framework for Inference-Layer Governability in Large Language Modelscs.AI0Open
Determined by User Needs: A Salient Object Detection Rationale Beyond Conventional Visual Stimulics.AI0Open
Explainable Model Routing for Agentic Workflowscs.AI0Open
Incentives shape how humans co-create with generative AIcs.AI0Open
LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steeringcs.AI0Open
Automated Analysis of Global AI Safety Initiatives: A Taxonomy-Driven LLM Approachcs.AI0Open
AgenticFlict: A Large-Scale Dataset of Merge Conflicts in AI Coding Agent Pull Requests on GitHubcs.AI0Open
CRAFT: Video Diffusion for Bimanual Robot Data Generationcs.AI0Open
Towards the AI Historian: Agentic Information Extraction from Primary Sourcescs.AI0Open
Focus Matters: Phase-Aware Suppression for Hallucination in Vision-Language Modelscs.AI0Open
Design Conditions for Intra-Group Learning of Sequence-Level Rewards: Token Gradient Cancellationcs.AI0Open
When Do Hallucinations Arise? A Graph Perspective on the Evolution of Path Reuse and Path Compressioncs.AI0Open
When Adaptive Rewards Hurt: Causal Probing and the Switching-Stability Dilemma in LLM-Guided LEO Satellite Schedulingcs.AI0Open
Personality Requires Struggle: Three Regimes of the Baldwin Effect in Neuroevolved Chess Agentscs.AI0Open