CoVEBench: Can Video Editing Models Handle Complex Instructions? Paper • 2606.08415 • Published 7 days ago • 48
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories Paper • 2606.02060 • Published 13 days ago • 54
T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation Paper • 2512.21094 • Published Dec 24, 2025 • 25