HALO: Human-Grounded Granular Evaluation of Proactive Agents Paper • 2610.39086 • Published 21 days ago • 12
Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models Paper • 2604.01444 • Published Apr 3 • 1
ProAR: Learning Prospective Reasoning with Autoregressive Video Models Paper • 2610.03664 • Published Oct 2 • 14
Semantic-Clipping: Efficient Vision-Language Modeling with Semantic-Guidedd Visual Selection Paper • 2503.11794 • Published Mar 14, 2025 • 1
ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails Paper • 2502.13458 • Published Feb 19, 2025 • 1
MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Design Paper • 2412.16270 • Published Dec 20, 2024
SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models Paper • 2412.04852 • Published Dec 6, 2024
Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset Paper • 2411.03554 • Published Nov 5, 2024
Unraveling Cross-Modality Knowledge Conflict in Large Vision-Language Models Paper • 2410.03659 • Published Oct 4, 2024 • 5
Multi-hop Evidence Retrieval for Cross-document Relation Extraction Paper • 2212.10786 • Published Dec 21, 2022 • 1
Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation Paper • 2409.12468 • Published Sep 19, 2024
Summarization as Indirect Supervision for Relation Extraction Paper • 2205.09837 • Published May 19, 2022 • 1
Learning Adaptive Reasoning Paths for Efficient Visual Reasoning Paper • 2604.14568 • Published Apr 16 • 10
ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models Paper • 2602.00154 • Published Jan 29
SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening Paper • 2605.17610 • Published May 17 • 1