Saif Punjwani
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1NLP×1
Frequent co-authors
Research Timeline
2026
Decoupling Exploration from Optimization in RLVR
This paper presents a framework called Exploration-Distillation (ExpDis) that decouples exploration from optimization in reinforcement learning to improve model quality and diversity.
Highlighted terms show continued research focus across papers