Siliang Zeng

Researcher, Seed-LLM-Posttrain, ByteDance Inc.

Joined

May 2021

Names

Siliang Zeng (Preferred)

Emails

****@umn.edu (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Researcher

Seed-LLM-Posttrain, ByteDance Inc. (bytedance.com)

2025 – Present

PhD student

Department of Electrical and Computer Engineering, University of Minnesota, Twin Cities (umn.edu)

2020 – 2025

Undergrad student

School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen (link.cuhk.edu.cn)

2016 – 2020

Advisors, Relations & Conflicts

PhD Advisor

Mingyi Hong

2020 – Present

Coauthor

Alfredo Garcia

2020 – Present

Expertise

Reinforcement Learning

Present

Inverse Reinforcement Learning

Present

Large Language Model

Present

Publications

Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Reward Design
Quan Wei, Siliang Zeng, Chenliang Li, William Brown, Oana Frunza, Wei Deng, Anderson Schneider, Yuriy Nevmyvaka, Yang Katie Zhao, Alfredo Garcia, Mingyi Hong
- Submitted to ICLR 2026
- Readers: Everyone
Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach
Xinnan Zhang, Chenliang Li, Siliang Zeng, Jiaxiang Li, Zhongruo Wang, Songtao Lu, Kaixiang Lin, Alfredo Garcia, Mingyi Hong
- Submitted to ICLR 2026
- Readers: Everyone
Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Reward Design and Credit Assignment
Quan Wei, Siliang Zeng, Chenliang Li, William Brown, Oana Frunza, Wei Deng, Yuriy Nevmyvaka, Yang Katie Zhao, Alfredo Garcia, Mingyi Hong
- MTI-LLM @ NeurIPS 2025 Poster
- Readers: Everyone
Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Credit Assignment
Siliang Zeng, Quan Wei, William Brown, Oana Frunza, Yuriy Nevmyvaka, Yang Katie Zhao, Mingyi Hong
- WCUA 2025 Poster
- Readers: Everyone
Bridging the Training-Inference Gap in LLMs by Leveraging Self-Generated Tokens
Zhepeng Cen, Yao Liu, Siliang Zeng, Pratik Chaudhari, Huzefa Rangwala, George Karypis, Rasool Fakoor
- SSI-FM Poster
- Readers: Everyone
Reinforcement Learning in Inference Time: A Perspective from Successive Policy Iterations
Xinnan Zhang, Chenliang Li, Siliang Zeng, Jiaxiang Li, Zhongruo Wang, Songtao Lu, Alfredo Garcia, Mingyi Hong
- Reasoning and Planning for LLMs @ ICLR2025
- Readers: Everyone
Bridging the Training-Inference Gap in LLMs by Leveraging Self-Generated Tokens
Zhepeng Cen, Yao Liu, Siliang Zeng, Pratik Chaudhari, Huzefa Rangwala, George Karypis, Rasool Fakoor
- Accepted by TMLR
- Readers: Everyone
Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality
Ruijia Zhang, Siliang Zeng, Chenliang Li, Alfredo Garcia, Mingyi Hong
- AISTATS 2025 Poster
- Readers: Everyone
Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment
Chenliang Li, Siliang Zeng, Zeyi Liao, Jiaxiang Li, Dongyeop Kang, Alfredo Garcia, Mingyi Hong
- FITML 2024 Poster
- Readers: Everyone
LLM Alignment Through Successive Policy Re-weighting (SPR)
Xinnan Zhang, Siliang Zeng, Jiaxiang Li, Kaixiang Lin, Mingyi Hong
- FITML 2024 Poster
- Readers: Everyone

View all 32 publications

Co-Authors

View all 44 co-authors