today local_bar

Dingcheng Li

Principal Researcher, Research, Baidu

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 6

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Reinforcement Learning with Backtracking Feedback

#4909 · Bilgehan Sel, Vaishakh Keshava, Phillip Wallis, Lukas Rutishauser, Ming Jin, Dingcheng Li

A backtracking method that reverts to safer points during generation, reducing safety violations