9:27From 4 Networks to 1 How DAPO Achieves Stable Training – 4 Experts Share Insights!OpenMMLab55 views·10 months ago
4:21Can the improvement of reasoning ability through RLVR be generalized to broader general intelligenceOpenMMLab33 views·10 months ago
10:09Can reinforcement learning truly raise the upper bound of model performanceOpenMMLab38 views·10 months ago
21:40Learning to Generate, Edit, and Enhance Images and Videos with MMagicOpenMMLab327 views·2 years ago
14:37Introduction to OpenDataLab： An Open Data Platform for Artificial IntelligenceOpenMMLab197 views·2 years ago
21:25OpenMMLab Open-source Platform for Vision, Language and Generative AIOpenMMLab806 views·2 years ago
26:08Learning to Generate, Edit, and Enhance Images and Videos with MMagicOpenMMLab605 views·2 years ago
17:28OpenMMLab 2.0 A General, Unified and Flexible Open-source Algorithm PlatformOpenMMLab935 views·2 years ago
12:09Introduction to OpenDataLab An Open Data Platform for Artificial IntelligenceOpenMMLab451 views·2 years ago
36:58Ruohui Wang Basic usage and overall architecture of OpenMMLab ｜AAAIOpenMMLab854 views·3 years ago
1:24:33通用视觉框架 OpenMMLab Lecture 5：Semantic segmentation and MMSegmentationOpenMMLab2.9K views·3 years ago
24:33[CVPR-2022] Haodong Duan Action Understanding in A Human-centric ViewOpenMMLab291 views·3 years ago
32:42[CVPR-2022] Hang Zhao Vision-centric 3D Perception for Scalable Autonomous DrivingOpenMMLab572 views·3 years ago
33:38[CVPR-2022] Han Hu Convergence of Architectures and Learning Methods in Computer VisionOpenMMLab123 views·3 years ago
![[CVPR-2022] Haodong Duan Action Understanding in A Human-centric View](https://i.ytimg.com/vi/prWKzDoR1MY/hqdefault.jpg?sqp=-oaymwEcCNACELwBSFXyq4qpAw4IARUAAIhCGAFwAcABBg==&rs=AOn4CLDpoy7BV8TsdxwYQCQ0Cj_UhPy9Ug)
![[CVPR-2022] Hang Zhao Vision-centric 3D Perception for Scalable Autonomous Driving](https://i.ytimg.com/vi/FC3XD0k5f-0/hqdefault.jpg?sqp=-oaymwEcCNACELwBSFXyq4qpAw4IARUAAIhCGAFwAcABBg==&rs=AOn4CLBc4O-JaKF6EgI76eJrYfEYMm6CMw)
![[CVPR-2022] Han Hu Convergence of Architectures and Learning Methods in Computer Vision](https://i.ytimg.com/vi/N0KG4Oc5cf4/hqdefault.jpg?sqp=-oaymwEcCNACELwBSFXyq4qpAw4IARUAAIhCGAFwAcABBg==&rs=AOn4CLABX5KxvUhKAOhAeK65flXX1E9GrA)
![[CVPR-2022] Chen Change Loy Improving Video Super-Resolution](https://i.ytimg.com/vi/8QnaFCrAJmk/hqdefault.jpg?sqp=-oaymwEcCNACELwBSFXyq4qpAw4IARUAAIhCGAFwAcABBg==&rs=AOn4CLCEqfchlTxozUqXDh_usOVoWi4B4A)