刘仁彪 Ren-Biao Liu Ph.D. candidate, LAMDA Group Supervisor: Professor Ming Li Major: Computer Science and Technology School of Artificial Intelligence National Key Laboratory for Novel Software Technology Nanjing University, Nanjing 210023, China Laboratory: Artificial Intelligence Building, Xianlin Campus of Nanjing University

Biography

Currently I am a final year Ph.D. student of School of Artificial Intelligence in Nanjing University and a member of LAMDA Group, led by professor Zhi-Hua Zhou.

I received my B.Sc. degree from School of Computer Science and Technology, Harbin Institute of Technology in June 2021. In the same year, I was admitted to pursue Ph.D. degree in Nanjing University without entrance examination.

Research Interests

My research interests include Machine Learning and Data Mining.
Especially:

• Large Language Model
• Transfer Learning
• Graph Neural Network

Publications

• Random Selection Reveals Implicit Knowledge Consensus in Code Generation.

  Ren-Biao Liu, Xin-Ye Li, Hui Sun, Yali Du, Jiang-Tian Xue, Ming Li.

  ICML, 2026




• Revisiting Chain-of-Thought in Code Generation: Do Language Models Need to Learn Reasoning before Coding?

  Ren-Biao Liu, Anqi Li, Chaoding Yang, Hui Sun, Ming Li.

  ICML, 2025




• Dynamic-Static Synergistic Selection Method for Candidate Code Solutions with Generated Test Cases.

  Ren-Biao Liu, Jiang-Tian Xue, Chao-Zeng Ma, Hui Sun, Xin-Ye Li, Ming Li.

  AAAI, 2026.




• ARBench: Algorithmic Reasoner or API Alchemist? Evaluating LLMs Beyond API Calls.

  Ren-Biao Liu, Chao-Zeng Ma, Anqi Li, Hui Sun, Xin-Ye Li, Ming Li.

  AAAI, 2026.




• TrustTrace: Modular Code Generation with Score-Guided Training and Trace-Aware Feedback.

  Ren-Biao Liu, Anqi Li, Xin-Ye Li, Hui Sun, Ming Li.

  Dream, 2026.




• Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation.

  Xin-Ye Li^*, Ren-Biao Liu^*, Yunji Zhang, Hui Sun, Zheng Xie, Ming Li.

  Arxiv, 2026.




• ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation.

  Hui Sun, Yun-Ji Zhang, Zheng Xie, Ren-Biao Liu, Yali Du, Xin-Ye Li, Ming Li.

  Arxiv, 2026.




• Probabilistic Instance Dependent Label Refinement for Noisy Label Learning.

  Hao-Yuan He, Yu Liu, Ren-Biao Liu, Ming Li.

  Machine Learning Journal, 2025

Awards & Honors

• National First Prize in the National Internet of Things Design Competition of Students: Garbage Classification System based on Deep Learning, 2020

• National Innovation and Entrepreneurship Training Programme of Students: Wise Information Technology system of Med based on Consortium Blockchain and Federated Learning, 2021

• The First International Algorithm Case Competition: Track of Data Selection and Label Correction. Winner Award (8th-place), 2022

• The Second International Algorithm Case Competition: Track of Continual Learning of Sequential Tasks. Winner Award (9th-place), 2023

Links

• Lamda2 Seminar (LAMDA members only)

Correspondence

• Email: liurb@lamda.nju.edu.cn

• Github: richardodliu

• Linkedin: Ren-Biao Liu

• Office: Room 423, Artificial Intelligence Building, Xianlin Campus of Nanjing University

• Address: National Key Laboratory for Novel Software Technology, Nanjing University, Xianlin Campus Mailbox 603, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China