Feng Yao

PhD student, University of California, San Diego

Joined

November 2021

Names

Feng Yao (Preferred)

Emails

****@gmail.com (Confirmed)

****@mails.tsinghua.edu.cn (Confirmed)

****@ucsd.edu (Confirmed)

Personal Links

Career & Education History

PhD student

University of California, San Diego (ucsd.edu)

2023 – 2028

MS student

Tsinghua University (tsinghua.edu.cn)

2020 – 2023

Advisors, Relations & Conflicts

PhD Advisor

Jingbo Shang

2023 – 2028

MS Advisor

Zhiyuan Liu

2020 – 2023

Expertise

Mixture of Experts

2024 – Present

Reinforcement Learning

2024 – Present

Large Language Model

2023 – Present

Publications

IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL
Zhoujun Cheng, Yutao Xie, Yuxiao Qu, Amrith Setlur, Shibo Hao, Varad Pimpalkhute, Tongtong Liang, Feng Yao, Zhengzhong Liu, Eric P. Xing, Virginia Smith, Ruslan Salakhutdinov, Zhiting Hu, Taylor W. Killian, Aviral Kumar
- SPOT
- Readers: Everyone
Finish First, Perfect Later: Test-Time Token-Level Cross-Validation for Diffusion Large Language Models
Runchu Tian, Junxia Cui, Xueqiang Xu, Feng Yao, Jingbo Shang
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
DenseMixer: Improving MoE Post-Training with Precise Router Gradient
Feng Yao, Junxia Cui, Ruohan Zhang, Liyuan Liu, Shibo Hao, Li Zhang, Chengyu Dong, Churan Zhi, Shuohang Wang, yelong shen, Jianfeng Gao, Jingbo Shang
- Submitted to ICLR 2026
- Readers: Everyone
Contamination Detection for VLMs Using Multi‑Modal Semantic Perturbations
Jaden Park, Mu Cai, Feng Yao, Jingbo Shang, Soochahn Lee, Yong Jae Lee
- ICLR 2026 Poster
- Readers: Everyone
On the Rollout-Training Mismatch in Modern RL Systems
Feng Yao, Liyuan Liu, Dinghuai Zhang, Chengyu Dong, Jingbo Shang, Jianfeng Gao
- NeurIPS 2025 ER Workshop Spotlight
- Readers: Everyone
TemporalBench: Evaluating Fine-Grained Temporal Dynamics Understanding for Multimodal Models
Mu Cai, Reuben Tan, Jianrui Zhang, Bocheng Zou, Kai Zhang, Feng Yao, Fangrui Zhu, Jing Gu, Yiwu Zhong, Yuzhang Shang, Yao Dou, Jaden Park, Jianfeng Gao, Yong Jae Lee, Jianwei Yang
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
On the Rollout-Training Mismatch in Modern RL Systems
Feng Yao, Liyuan Liu, Dinghuai Zhang, Chengyu Dong, Jingbo Shang, Jianfeng Gao
- NeurIPS 2025 Workshop
- Readers: Everyone
DenseMixer: Improving MoE Post-Training with Precise Router Gradient
Feng Yao, Junxia Cui, Ruohan Zhang, Liyuan Liu, Shibo Hao, Li Zhang, Chengyu Dong, Shuohang Wang, yelong shen, Jianfeng Gao, Jingbo Shang
- SPIGM @ NeurIPS
- Readers: Everyone
Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
Zhoujun Cheng, Shibo Hao, Tianyang Liu, Fan Zhou, Yutao Xie, Feng Yao, Yuexin Bian, Nilabjo Dey, Yonghao Zhuang, Yuheng Zha, Yi Gu, Kun Zhou, Yuqi Wang, Yuan Li, Richard Fan, Jianshu She, Chengqian Gao, Abulhair Saparov, Taylor W. Killian, Haonan Li et al. (4 additional authors not shown)
- NeurIPS 2025 Datasets and Benchmarks Track poster
- Readers: Everyone
Training Language Models to Generate Quality Code with Program Analysis Feedback
Feng Yao, Zilong Wang, Liyuan Liu, Junxia Cui, Li Zhong, Xiaohan Fu, Haohui Mai, Vish Krishnan, Jianfeng Gao, Jingbo Shang
- NeurIPS 2025 poster
- Readers: Everyone

View all 33 publications

Co-Authors

View all 126 co-authors