TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs Paper • 2607.17423 • Published 30 days ago • 167
iOSWorld: A Benchmark for Personally Intelligent Phone Agents Paper • 2606.09764 • Published Jun 8 • 4
SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search Paper • 2605.29796 • Published May 28 • 25
VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions Paper • 2605.27141 • Published May 26 • 20
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 433
ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling Paper • 2603.25746 • Published Mar 26 • 155
SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models Paper • 2603.16859 • Published Mar 17 • 248