The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents Paper • 2604.10577 • Published 5 days ago • 23
AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories Paper • 2504.08942 • Published Apr 11, 2025 • 28
SmolVLM: Redefining small and efficient multimodal models Paper • 2504.05299 • Published Apr 7, 2025 • 207
BM25S: Orders of magnitude faster lexical search via eager sparse scoring Paper • 2407.03618 • Published Jul 4, 2024 • 14
Learning Action and Reasoning-Centric Image Editing from Videos and Simulations Paper • 2407.03471 • Published Jul 3, 2024 • 30