Author

Kaichen Zhang

Observed name: Zhang, Kaichen

Institution: University of Hong Kong

Observed institution: University of Hong Kong

OpenAlex ID: A5136654661

GVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation

2026 · Zhang, Kaichen, Hong, Yuzhong, et al. · arXiv (Cornell University)

ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning

2026 · Yang, Zuhao, Zhang, Kaichen, et al. · arXiv (Cornell University)

Quality-constrained Entropy Maximization Policy Optimization for LLM Diversity

2026 · Pan, Haihui, Hong, Yuzhong, et al. · arXiv (Cornell University)

Works count: 3

Citation count:

H-index:

I10-index: