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
Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning Paper • 2509.23873 • Published Sep 28, 2025 • 68