-
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs
Paper • 2607.17423 • Published • 38 -
MCG-NJU/TimeLens2-93K
Viewer • Updated • 71.4k • 828 • 8 -
MCG-NJU/TimeLens2-8B
Video-Text-to-Text • 9B • Updated • 718 • 9 -
MCG-NJU/TimeLens2-4B
Video-Text-to-Text • 4B • Updated • 193 • 8
AI & ML interests
Computer Vision; Video Understanding; Action Recognition
Recent Activity
Papers
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
Organization Card
We release the code, model and data of the research work done by the Multimedia Computing Group (MCG), Nanjing University🔥
-
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
Paper • 2607.14935 • Published • 158 -
MCG-NJU/I3D-ViT
Image Feature Extraction • 0.4B • Updated • 73 • 9 -
MCG-NJU/VideoChat3-4B
Video-Text-to-Text • 4B • Updated • 573 • 16 -
MCG-NJU/VideoChat3-LV116k
Viewer • Updated • 8.07k • 8.51k • 12
-
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs
Paper • 2607.17423 • Published • 38 -
MCG-NJU/TimeLens2-93K
Viewer • Updated • 71.4k • 828 • 8 -
MCG-NJU/TimeLens2-8B
Video-Text-to-Text • 9B • Updated • 718 • 9 -
MCG-NJU/TimeLens2-4B
Video-Text-to-Text • 4B • Updated • 193 • 8
-
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
Paper • 2607.14935 • Published • 158 -
MCG-NJU/I3D-ViT
Image Feature Extraction • 0.4B • Updated • 73 • 9 -
MCG-NJU/VideoChat3-4B
Video-Text-to-Text • 4B • Updated • 573 • 16 -
MCG-NJU/VideoChat3-LV116k
Viewer • Updated • 8.07k • 8.51k • 12
models 52
MCG-NJU/TimeLens2-2B
Video-Text-to-Text • 2B • Updated • 48 • 5
MCG-NJU/TimeLens2-4B
Video-Text-to-Text • 4B • Updated • 193 • 8
MCG-NJU/TimeLens2-8B
Video-Text-to-Text • 9B • Updated • 718 • 9
MCG-NJU/VideoChat3-4B
Video-Text-to-Text • 4B • Updated • 573 • 16
MCG-NJU/I3D-ViT
Image Feature Extraction • 0.4B • Updated • 73 • 9
MCG-NJU/Video-o3_RL
Video-Text-to-Text • 8B • Updated • 31 • 2
MCG-NJU/Video-o3_SFT_RL
Video-Text-to-Text • 8B • Updated • 228 • 2
MCG-NJU/Video-o3-SFT-Stage2-Data
Updated
MCG-NJU/Video-o3-SFT-Stage1-Data
Updated
MCG-NJU/LongVPO-Stage2-InternVL3-8B
Video-Text-to-Text • 8B • Updated • 4
datasets 20
MCG-NJU/TimeLens2-93K
Viewer • Updated • 71.4k • 828 • 8
MCG-NJU/VideoChat3-LV116k
Viewer • Updated • 8.07k • 8.51k • 12
MCG-NJU/VideoChat3-Academic2M
Viewer • Updated • 19.2k • 2.15k • 20
MCG-NJU/Seeker-173K
Preview • Updated • 295 • 5
MCG-NJU/VIABench
Preview • Updated • 675 • 3
MCG-NJU/VideoChat3-OL617k
Preview • Updated • 325 • 9
MCG-NJU/ODV-Bench
Viewer • Updated • 6.35k • 668
MCG-NJU/StreamForest-Annodata
Updated • 92 • 1
MCG-NJU/LongVPO-Training-Data
Viewer • Updated • 14.5k • 39
MCG-NJU/SportsGrounding
Updated • 28