WithEveryone: Unified Planning and Identity Grounding for Group Image Generation Paper • 2608.20336 • Published 2 days ago • 38
HarmProfile: Characterizing Harmful Distributions in Frontier LLMs Paper • 2608.14577 • Published Jun 11 • 20
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents Paper • 2604.02947 • Published Apr 3 • 19