DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
NeurIPS 2024, Oral at FM-Wild ICML 2024 (3%)
Hao Bai*, Yifei Zhou* (equal contribution), Mert Cemri, Jiayi Pan, Alane Suhr, Sergey Levine, Aviral Kumar
Publications
Aligning Large Language Models with Representation Editing: A Control Perspective
NeurIPS 2024
Lingkai Kong*, Haorui Wang*, Wenhao Mu*, Yuanqi Du, Yuchen Zhuang, Yifei Zhou, Yue Song, Rongzhi Zhang, Kai Wang, Chao Zhang
Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
NeurIPS 2024
Yuexiang Zhai, Hao Bai, Zipeng Lin, Jiayi Pan, Shengbang Tong, Yifei Zhou, Alane Suhr, Saining Xie, Yann Lecun, Yi Ma, Sergey Levine
Autonomous Evaluation and Refinement of Digital Agents
COLM 2024, Best Papar Award at MAR CVPR 2024
Jiayi Pan, Yichi Zhang, Nicolas Tomlin, Yifei Zhou, Sergey Levine, Alane Suhr
ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL
ICML 2024
Yifei Zhou, Andrea Zanette, Jiayi Pan, Sergey Levine, Aviral Kumar
Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees
ICLR 2024
Yifei Zhou*, Ayush Sekhari* , Yuda Song, Wen Sun
Distribution Normalization: An “Effortless” Test-Time Augmentation for Contrastively Learned Visual-language Models
NeurIPS 2023
Yifei Zhou*, Juntao Ren*, Fengyu Li*, Ramin Zabih, Ser-Nam Lim
BT^2: Backward-compatible Training with Basis Transformation
ICCV 2023
Yifei Zhou*, Zilu Li*, Abhinav Shrivastava, Hengshuang Zhao, Antonio Torralba, Taipeng Tian, Ser-Nam Lim
Hybrid RL: Using offline data can make online RL efficient
ICLR 2023
Yuda Song*, Yifei Zhou* , Ayush Sekhari, J. Andrew Bagnell, Akshay Krishnamurthy, Wen Sun
GAPX: Generalized Autoregressive Paraphrase-identification X
NeurIPS 2022
Yifei Zhou, Renyu Li, Hayden Housen, and Sernam Lim
Improve Discourse Dependency Parsing with Contextualized Representations
NAACL 2022 (findings)
Yifei Zhou, Yansong Feng