CVPR 2026 BlackSwan Challenge. V-JEPA 2 cross-modal probes + Qwen2.5-VL pipelines for video reasoning. 82.5% Detective accuracy.
0
stars
1
commits
Python
primary language
Apr 19, 2026
updated
1 commits
Dongyh35/CVBench
2
Hokhim2/CVBench
19
TencentARC/Video-Holmes
[ECCV 2026] Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
99
yeliudev/VideoMind
🧠 VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning (ICLR 2026)
356
Becomebright/GroundVQA
4
Video-R1/Video-R1-eval
6
longvideobench/LongVideoBench
51
tulerfeng/Video-R1
Video-R1: Reinforcing Video Reasoning in MLLMs [🔥the first paper to explore R1 for video]
888
84.1%
Shell
14.8%
Jinja
1.1%
