OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning Paper • 2606.08572 • Published 3 days ago • 8
CoVEBench: Can Video Editing Models Handle Complex Instructions? Paper • 2606.08415 • Published 3 days ago • 38 • 2
CoVEBench: Can Video Editing Models Handle Complex Instructions? Paper • 2606.08415 • Published 3 days ago • 38
CoVEBench: Can Video Editing Models Handle Complex Instructions? Paper • 2606.08415 • Published 3 days ago • 38
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills Paper • 2606.07412 • Published 5 days ago • 8
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories Paper • 2606.02060 • Published 9 days ago • 52 • 7