AI & ML interests
None defined yet.
Recent Activity
Papers
DR$^{3}$-Eval: Towards Realistic and Reproducible Deep Research Evaluation
CodeTracer: Towards Traceable Agent States
models 0
None public yet
datasets 9
NJU-LINK/WebCompass
Viewer • Updated • 933 • 1.96k • 3
NJU-LINK/DR3-Eval
Viewer • Updated • 100 • 1.72k • 2
NJU-LINK/CodeTraceBench
Viewer • Updated • 4.32k • 4.8k • 2
NJU-LINK/ViDiC-1K
Updated • 250 • 5
NJU-LINK/OmniVideoBench
Viewer • Updated • 1k • 2.23k • 4
NJU-LINK/camerabench_binary
Viewer • Updated • 7.83k • 16
NJU-LINK/MT-Video-Bench
Updated • 69 • 4
NJU-LINK/T2AV-Compass
Viewer • Updated • 500 • 84 • 4
NJU-LINK/IF-VidCap
Viewer • Updated • 1.4k • 455 • 2