NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#diffusionart

0 stories this week · 1 this month · 1 in 6 months · mostly AI

Stories per day · 30 days

Relateddiffusion-models1 hunyuanvideo1 reinforcement-learning1 reward-tilting1 video-generation1

1 stories, newest first · one card per story

Hugging Face daily papers18d ago

DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models

DiffusionART stably reinforces diffusion models without EMA tuning, matching HunyuanVideo-13B rewards with about 12 times fewer GPU hours.

diffusion-models reinforcement-learning

3