Victor Ma
Orcid: 0009-0000-6597-7582
According to our database1,
Victor Ma authored at least 3 papers
between 2025 and 2026.
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2026
2025
CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization.
CoRR, August, 2025
CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025