today local_bar

Sid Wang

Researcher, Meta

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Beyond Verifiable Rewards: Scaling Reinforcement Learning in Language Models to Unverifiable Data

#507 · Yunhao Tang, Sid Wang, Lovish Madaan, Remi Munos

Scaling RL-based reasoning to unverifiable data