RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling
RewardVerse uses dynamic rubrics and RGPO to stabilize video reward scores and reduce scalar drift.
1 stories, newest first · one card per story
RewardVerse uses dynamic rubrics and RGPO to stabilize video reward scores and reduce scalar drift.
Today 1.6K readers · 2.5K views · 780 reads · all time 189K views