‪Northwestern University‬ - ‪‪Cited by 256‬‬ - ‪large language models‬ - ‪reinforcement learning‬ - ‪offline learning‬ - ‪online learning‬

2024年5月26日 · View a PDF of the paper titled Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer, by Zhihan Liu and 7 other authors

Promoting openness in scientific communication and the peer-review process

Zhihan LIU, Professor (Associate) | Cited by 22 | of Central South University, Changsha (CSU) | Read 13 publications | Contact Zhihan LIU

2021年8月19日 · View a PDF of the paper titled Provably Efficient Generative Adversarial Imitation Learning for Online and Offline Setting with Linear Function Approximation, by Zhihan Liu and 4 other authors

Empirical Evidence from Patient Satisfaction.

Experience: Meta · Education: Columbia University in the City of New York · Location: San Francisco Bay Area · 354 connections on LinkedIn. View Zhihan Liu’s profile on LinkedIn, a professional...

ACM Transactions on Multimedia Computing, Communications, and Applications …

I am a Senior research scientist at Nvidia Applied Deep Learning Research (ADLR) Team. I received Bachelor Degree from Zhejiang University, and Ph.D. Degree from the Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology under the supervision of Prof. Pascale Fung in Center of AI Research.

Zhihan LIU | Cited by 1,446 | of Beijing University of Posts and Telecommunications, Beijing (BUPT) | Read 55 publications | Contact Zhihan LIU