REinforcement Learning EXtrapolation (RELEX)

AI & ML interests

None defined yet.

Recent Activity

weizhepei  updated a model about 1 month ago

relex-rlvr/RLVR-Qwen2.5-Math-1.5B

weizhepei  submitted a paper about 1 month ago

You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories

weizhepei  updated a model about 1 month ago

relex-rlvr/RLVR-Qwen3-4B-Base

View all activity

Team members 1