Kaiyuan Li

MS student, nanjing university

Joined

May 2023

Names

Kaiyuan Li (Preferred)

Emails

****@qq.com (Confirmed)

****@lamda.nju.edu.cn (Confirmed)

Personal Links

Career & Education History

MS student

nanjing university (nju.edu.cn)

2024 – Present

Undergrad student

nanjing university (nju.edu.cn)

2020 – 2024

Advisors, Relations & Conflicts

No relations added

Expertise

Robotics

2024 – Present

Reinforcement Learning

2023 – Present

Large language model

2023 – Present

Publications

RLVR Training of LLMs Does Not Improve Thinking Ability for General QA: Evaluation Method and a Simple Solution
Kaiyuan Li, Jing-Cheng Pang, Yang Yu
- ICML 2026 FoGen Workshop Poster
- Readers: Everyone
WHALE: Towards Generalizable and Scalable World Models for Embodied Decision-making
Zhilong Zhang, Ruifeng Chen, Junyin Ye, Yihao Sun, Haoxiang Ren, Xinghao Du, Pengyuan Wang, Jing-Cheng Pang, Kaiyuan Li, Tian-Shuo Liu, Haoxin Lin, Yang Yu, Zhi-Hua Zhou
- NeurIPS 2025 Workshop EWM
- Readers: Everyone
ImagineBench: Evaluating Reinforcement Learning with Large Language Model Rollouts
Jing-Cheng Pang, Kaiyuan Li, Yidi Wang, Si-Hang Yang, Shengyi Jiang, Yang Yu
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Whale-X: Learning Scalable Embodied World Models with Enhanced Generalizability
Zhilong Zhang, Ruifeng Chen, Junyin Ye, Yihao Sun, Pengyuan Wang, Jing-Cheng Pang, Kaiyuan Li, Tian-Shuo Liu, Haoxin Lin, Yang Yu
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Learning View-invariant World Models for Visual Robotic Manipulation
Jing-Cheng Pang, Nan Tang, Kaiyuan Li, Yuting Tang, Xin-Qiang Cai, Zhen-Yu Zhang, Gang Niu, Masashi Sugiyama, Yang Yu
- ICLR 2025 Poster
- Readers: Everyone
KALM: Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts
Jing-Cheng Pang, Si-Hang Yang, Kaiyuan Li, Jiaji Zhang, Xiong-Hui Chen, Nan Tang, Yang Yu
- NeurIPS 2024 poster
- Readers: Everyone
Language Model Self-improvement by Reinforcement Learning Contemplation
Jing-Cheng Pang, Pengyuan Wang, Kaiyuan Li, Xiong-Hui Chen, Jiacheng Xu, Zongzhang Zhang, Yang Yu
- ICLR 2024 poster
- Readers: Everyone

Kaiyuan Li

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

RLVR Training of LLMs Does Not Improve Thinking Ability for General QA: Evaluation Method and a Simple Solution

WHALE: Towards Generalizable and Scalable World Models for Embodied Decision-making

ImagineBench: Evaluating Reinforcement Learning with Large Language Model Rollouts

Whale-X: Learning Scalable Embodied World Models with Enhanced Generalizability

Learning View-invariant World Models for Visual Robotic Manipulation

KALM: Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts

Language Model Self-improvement by Reinforcement Learning Contemplation

Co-Authors