ROSS: Relearning from Self-Generated Rollouts through Selective Supervision
Paper • 2609.35954 • Published • 26
Jiayan Fu
Eclipse25
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
ROSS: Relearning from Self-Generated Rollouts through Selective Supervision upvoted a paper about 1 month ago
PACT: From Credit Assignment to Critic AlignmentOrganizations
upvoted 2
papers about 1 month ago