Alexander Bukharin
3
Papers
133
Total Citations
Papers (3)
HelpSteer2-Preference: Complementing Ratings with Preferences
ICLR 2025
102
citations
HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages
NeurIPS 2025
31
citations
Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms
NeurIPS 2023
0
citations