Video Edit Paper
AI & ML interests
None defined yet.
Recent Activity
Papers
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning
-
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 • 15 -
NJU-LINK/DR3-Eval
Viewer • Updated • 100 • 1.49k • 2 -
TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation
Paper • 2606.02320 • Published • 15
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 • 15 -
NJU-LINK/DR3-Eval
Viewer • Updated • 100 • 1.49k • 2 -
TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation
Paper • 2606.02320 • Published • 15
datasets 16
NJU-LINK/AVSCapBench
Viewer • Updated • 1.23k • 729 • 1
NJU-LINK/AVE-Compass
Viewer • Updated • 196 • 53 • 2
NJU-LINK/OmniCap-IF-54K
Viewer • Updated • 53.9k • 104
NJU-LINK/OmniCap-IF
Viewer • Updated • 480 • 401 • 1
NJU-LINK/CoVEBench
Viewer • Updated • 626 • 1.05k • 2
NJU-LINK/TELBench
Updated • 7k • 2
NJU-LINK/TVIR-Bench
Viewer • Updated • 100 • 72
NJU-LINK/WebCompass
Viewer • Updated • 933 • 3.24k • 6
NJU-LINK/ViDiC-1K
Updated • 102 • 5
NJU-LINK/DR3-Eval
Viewer • Updated • 100 • 1.49k • 2