ddz16/CamInject-8B
Video-Text-to-Text • 9B • Updated • 20
🔄 In a Training Loop
dudazhao
ddz16
AI & ML interests
None yet
Recent Activity
authored a paper about 1 month ago
Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation authored a paper about 1 month ago
WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models authored a paper about 1 month ago
WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World ModelsOrganizations
None yet
ddz16/CamDistill-8B
Video-Text-to-Text • 9B • Updated • 49
ddz16/CamSFT-8B
Video-Text-to-Text • 9B • Updated • 23
ddz16/CamInject-4B
Video-Text-to-Text • 4B • Updated • 22
ddz16/CamDistill-4B
Video-Text-to-Text • 5B • Updated • 42
ddz16/CamSFT-4B
Video-Text-to-Text • 4B • Updated • 33
ddz16/Qwen3-VL-8B-GRPO
Video-Text-to-Text • 770k • Updated • 7
ddz16/Qwen3-VL-8B-ArrowRL
Video-Text-to-Text • 770k • Updated • 7
ddz16/Qwen3-VL-8B-TGRPO
Video-Text-to-Text • 770k • Updated • 10
ddz16/Qwen3-VL-4B-ArrowRL
Video-Text-to-Text • 570k • Updated • 17
ddz16/Qwen3-VL-4B-TGRPO
Video-Text-to-Text • 570k • Updated • 11
ddz16/Qwen3-VL-4B-GRPO
Video-Text-to-Text • 570k • Updated • 9
ddz16/Qwen3-VL-8B-CRPO
Video-Text-to-Text • 770k • Updated • 41
ddz16/Qwen3-VL-4B-CRPO
Video-Text-to-Text • 570k • Updated • 40