Runji Lin

Email: linrunji2021 [at] ia.ac.cn

Fields of Interest: Reinforcement Learning, Multi-Agent System, Large Language Models

Runji Lin

Short Bio

Runji Lin is currently pursuing his MSc degree at the School of Artificial Intelligence, University of Chinese Academy of Sciences, China. His research interests include reinforcement learning, multi-agent system, and Large Language Models. He participated in the development of the Qwen series of large language models, mainly involving in the RLHF alignment of LLM, as well as the development of integrating large models as agents with external systems.

Experience

Research Intern at Alibaba Qwen Team

2022.11 - Present

Algorithm Engineer Intern at NetEase

2020.07 - 2020.08

Publications

Large language models play starcraft ii: Benchmarks and a chain of summarization approach

W Ma, Q Mi, X Yan, Y Wu, R Lin, H Zhang, J Wang arXiv preprint

arXiv:2312.11865, 2023 - View Paper

Routing to the expert: Efficient reward-guided ensemble of large language models

K Lu, H Yuan, R Lin, J Lin, Z Yuan, C Zhou, J Zhou

arXiv preprint - arXiv:2311.08692, 2023 - View Paper

# InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models

K Lu, H Yuan, Z Yuan, R Lin, J Lin, C Tan, C Zhou, J Zhou

ICLR 2023 - View Paper

Qwen technical report

J Bai, S Bai, Y Chu, Z Cui, K Dang, X Deng, Y Fan, W Ge, Y Han, F Huang, R Lin...

arXiv preprint - arXiv:2309.16609, 2023 - View Paper

Learn to Flap: Foil Non-parametric Path Planning via Deep Reinforcement Learning

ZP Wang*, RJ Lin*, ZY Zhao, PM Guo, N Yang, DX Fan

Journal of Fluid Mechanics, 2023 - View Paper

Large Sequence Models for Sequential Decision-Making: A Survey

M WEN*, R Lin*, H WANG, Y YANG, Y WEN, L MAI, J WANG, H ZHANG, ...

Frontiers of Computer Science, 2023 - View Paper

Contextual Transformer for Offline Meta Reinforcement Learning

R Lin, Y Li, X Feng, Z Zhang, XHW Fung, H Zhang, J Wang, Y Du, Y Yang

NeurIPS 2022 Workshop: Foundation Models for Decision Making, 2022 - View Paper

Scalable Model-based Policy Optimization for Decentralized Networked Systems

Y Du, C Ma, Y Liu, R Lin, H Dong, J Wang, Y Yang

IROS 2022 - View Paper

Multi-Agent Reinforcement Learning is a Sequence Modeling Problem

M Wen, JG Kuba, R Lin, W Zhang, Y Wen, J Wang, Y Yang

NeurIPS 2022 - View Paper

Increasing the Data Rate for Reflected Optical Camera Communication Using Uniform LED Light

Z Chen*, R Lin*, H Duan, Y Chen, Y Yang, R Wu, L Chen

IEEE INFOCOM 2020-IEEE Conference on Computer Communications Workshops, 2020 - View Paper