arxiv:2608.10932
🔄 In a Training Loop
dudazhao
ddz16
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation authored a paper 1 day ago
WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models authored a paper 1 day ago
WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World ModelsOrganizations
None yet
models 18
ddz16/CamInject-8B
Video-Text-to-Text • 9B • Updated • 21
ddz16/CamDistill-8B
Video-Text-to-Text • 9B • Updated • 61
ddz16/CamSFT-8B
Video-Text-to-Text • 9B • Updated • 28
ddz16/CamInject-4B
Video-Text-to-Text • 4B • Updated • 20
ddz16/CamDistill-4B
Video-Text-to-Text • 5B • Updated • 29
ddz16/CamSFT-4B
Video-Text-to-Text • 4B • Updated • 22
ddz16/Qwen3-VL-8B-GRPO
Video-Text-to-Text • 770k • Updated • 17
ddz16/Qwen3-VL-8B-ArrowRL
Video-Text-to-Text • 770k • Updated • 20
ddz16/Qwen3-VL-8B-TGRPO
Video-Text-to-Text • 770k • Updated • 20
ddz16/Qwen3-VL-4B-ArrowRL
Video-Text-to-Text • 570k • Updated • 15