You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
Paper • 2605.21468 • Published • 51
PP
PassionPrc
AI & ML interests
None yet
Recent Activity
updated a dataset 7 days ago
PassionPrc/hotpot-fine-grain-evidence published a dataset 7 days ago
PassionPrc/hotpot-fine-grain-evidence updated a dataset 18 days ago
PassionPrc/docvqa-grpoOrganizations
None yet
upvoted a paper about 1 month ago