Video Edit Paper
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
TestPrism: Rethinking Test Evaluation Beyond a Single Reference
AVE-Compass: Towards Holistic Evaluation for Audio-Video Editing Abilities
-
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories
Paper • 2606.02060 • Published • 58 -
MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?
Paper • 2606.01993 • Published • 16 -
NJU-LINK/DR3-Eval
Viewer • Updated • 100 • 6.5k • 2 -
TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation
Paper • 2606.02320 • Published • 12
Video Edit Paper
-
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories
Paper • 2606.02060 • Published • 58 -
MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?
Paper • 2606.01993 • Published • 16 -
NJU-LINK/DR3-Eval
Viewer • Updated • 100 • 6.5k • 2 -
TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation
Paper • 2606.02320 • Published • 12
datasets 16
NJU-LINK/MT-Video-Bench
Updated • 241 • 6
NJU-LINK/AVE-Compass-v2
Viewer • Updated • 196 • 461 • 2
NJU-LINK/AVSCapBench
Viewer • Updated • 1.23k • 2.59k • 1
NJU-LINK/OmniCap-IF-54K
Viewer • Updated • 53.9k • 463
NJU-LINK/OmniCap-IF
Viewer • Updated • 480 • 243 • 1
NJU-LINK/CoVEBench
Viewer • Updated • 626 • 651 • 2
NJU-LINK/TELBench
Updated • 426 • 2
NJU-LINK/TVIR-Bench
Viewer • Updated • 100 • 87
NJU-LINK/WebCompass
Viewer • Updated • 933 • 1.97k • 6
NJU-LINK/ViDiC-1K
Updated • 171 • 5