MEND: RL For Flow Models via Proximal Velocity Matching
MEND post-trains flow models with proximal velocity matching, beating Flow-GRPO and ReFL in far fewer updates.
1 stories, newest first · one card per story
MEND post-trains flow models with proximal velocity matching, beating Flow-GRPO and ReFL in far fewer updates.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views