Hugging Face's logo

billyenrizky
/
ReFusion-8B-MDPO

Reinforcement Learning
Safetensors
discrete-flow-matching
web-action-planning
formfactory
openbrowser
sequence-level-rl
Model card Files
xet
 Community
ReFusion-8B-MDPO
460 MB
  • 1 contributor
 History: 3 commits
billyenrizky's picture
billyenrizky
Update research title to: Concentrate or Collapse
2da374e verified