RL finetuning for Wan-based models
🔄 In a Training Loop
Yushi Huang
Harahan
AI & ML interests
Efficient AIGC, especially for video/image generation and MLLMs
Recent Activity
upvoted a paper 2 days ago
Recursive Synthesis for Long-Horizon Terminal Tasks updated a collection 13 days ago
GenRL updated a collection 13 days ago
GenRLOrganizations
models 7
Harahan/MeanFlowNFT
Text-to-Image • Updated • 1
Harahan/FLUX1-12B-RTDMD
Text-to-Image • Updated • 2
Harahan/FLUX2-9B-RTDMD
Text-to-Image • Updated • 1
Harahan/FLUX2-4B-RTDMD
Text-to-Image • Updated • 4
Harahan/SD35M-RTDMD
Text-to-Image • Updated • 1
Harahan/QVGen-CogVideoX-2B-W4A4
Text-to-Video • 2B • Updated • 948 • 2
Harahan/QVGen-Wan-1_3B-W4A4
Text-to-Video • 1B • Updated • 19 • 2
datasets 0
None public yet