Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories Paper • 2606.02060 • Published 6 days ago • 50
T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation Paper • 2512.21094 • Published Dec 24, 2025 • 25
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