Mo Guang

Researcher, Li Auto Inc.

Joined

March 2025

Names

Mo Guang (Preferred)

Emails

****@lixiang.com (Confirmed)

Personal Links

DBLP

ORCID

Career & Education History

Researcher

Li Auto Inc. (lixiang.com)

2024 – Present

Researcher

Bosch (bosch.com)

2023 – 2024

Researcher

Alibaba Group (alibaba-inc.com)

2018 – 2022

Postdoc

Tsinghua University (cs.tsinghua.edu.cn)

2016 – 2018

PhD student

Computer Science, Tsinghua University (cs.tsinghua.edu.cn)

2010 – 2016

Advisors, Relations & Conflicts

Coworker

Yaqian Li

2024 – 2025

Expertise

Computer vision

2014 – 2025

Publications

SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs
Yanxiao Zhao, Yaqian Li, Zi-Hao Bo, Rinyoichi Takezoe, Haojia Hui, Mo Guang, Lei Ren, Xiaolin Qin, Kaiwen Long
- ICLR 2026 Workshop LLM Reasoning
- Readers: Everyone
A 56-Gb/s, 6.3-pJ/bit PAM-4 DFB Laser Driver Incorporating Asymmetric Equalization and Integrated CDR in 28 nm CMOS
Yang Min, Nan Qi, Yihan Chen, Yi Zhang, Minye Zhu, Guike Li, Yonghui Lin, Huiyao Peng, Mo Guang, Kaiwen Long, Zhao Zhang, Jian Liu, Nanjian Wu, Jingbo Shi, Yong Chen, Frank F. Shi, Liyuan Liu
- IEEE Trans. Very Large Scale Integr. Syst. 2025
- Readers: Everyone
LearnPruner: Rethinking Attention-based Token Pruning in Vision Language Models
Rinyoichi Takezoe, Yaqian Li, Zi-Hao Bo, Anzhou Hou, Mo Guang, Kaiwen Long
- ICLR 2026 Poster
- Readers: Everyone
BlockSpec: Blockwise Speculative Decoding for Diffusion LLMs
Tianxiang Pan, Baitao Gong, Mo Guang, Hongwei Yong, Tianpeng Jiang, Yaqian Li, Zheng Cao, Kaiwen Long
- Submitted to ICLR 2026
- Readers: Everyone
RE-PO: Robust Enhanced Policy Optimization as a General Framework for LLM Alignment
Xiaoyang Cao, Zelai Xu, Mo Guang, Kaiwen Long, Michiel A. Bakker, Yu Wang, Chao Yu
- ICLR 2026 Poster
- Readers: Everyone
SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling
Yixian Zhang, Shu'ang Yu, Tonghe Zhang, Mo Guang, Haojia Hui, Kaiwen Long, Yu Wang, Chao Yu, Wenbo Ding
- ICLR 2026 Poster
- Readers: Everyone
MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs
Huining Yuan, Zelai Xu, Zheyue Tan, Xiangmin Yi, Mo Guang, Kaiwen Long, Haojia Hui, Boxun Li, Xinlei Chen, Bo Zhao, Xiao-Ping Zhang, Chao Yu, Yu Wang
- ICLR 2026 Poster
- Readers: Everyone
VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments
Zelai Xu, Zhexuan Xu, Xiangmin Yi, Huining Yuan, Mo Guang, Kaiwen Long, Xinlei Chen, Yi Wu, Chao Yu, Yu Wang
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
Latent Collective Preference Optimization: A General Framework for Robust LLM Alignment
Xiaoyang Cao, Zelai Xu, Mo Guang, Kaiwen Long, Michiel A. Bakker, Yu Wang, Chao Yu
- CoRR 2025
- Readers: Everyone
SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs
Yanxiao Zhao, Yaqian Li, Zihao Bo, Rinyoichi Takezoe, Haojia Hui, Mo Guang, Lei Ren, Xiaolin Qin, Kaiwen Long
- CoRR 2025
- Readers: Everyone

View all 11 publications

Co-Authors

View all 48 co-authors