Han Lu (陆晗)

I received my Ph.D. in Computer Science from Shanghai Jiao Tong University (SJTU) in 2026, advised by Prof. Junchi Yan. I received my B.Eng. from ACM Class in SJTU. Prior to that, I won the NOI 2016 Silver Medal and APIO 2016 Gold Medal. My research focuses on combinatorial optimization, reinforcement learning for LLMs, and LLM pretraining. I have published 9 papers at top-tier venues (NeurIPS, ICLR, CVPR, SIGMOD, TPAMI). I had internships at Huawei Noah's Ark, Bilibili, ByteDance, and Alibaba.

Currently, I have joined Meituan LongCat Team working on LLM Pretraining.

GitHub Google Scholar Email QQ

Research Interests

Reinforcement Learning for LLMs LLM Pretraining Combinatorial Optimization Data-Centric AI

Industry & Internship Experience

Alibaba — Future Life Lab (T-Star)

Jun 2025 – Oct 2025

Asynchronous RL framework design for LLM reasoning; off-policy RL for RLVR acceleration.

ByteDance — Douyin Recommendation (Ranking)

Mar 2025 – Jun 2025

Exploring scalable architectures (FFN, MoE, Transformer) for long-sequence user modeling in ranking models.

Bilibili — Foundation Model Group

Jun 2024 – Feb 2025

LLM continual pretraining, MoE model deployment on GPU/NPU, AI-assisted dubbing with LLMs.

Huawei Noah's Ark Lab — Decision & Reasoning

Jun 2020 – Dec 2020

RL-based online parameter tuning for storage systems. Published at SIGMOD 2021. Outstanding Intern Award.

Publications

ROLL Flash — Accelerating RLVR and Agentic Training with Asynchrony

Han Lu*, Zichen Liu*, Shaopan Xiong*, Yancheng He*, Wei Gao*, Yanan Wu*, Weixun Wang*, Jiashun Liu, Yang Li, Haizhou Zhao, Ju Huang, Siran Yang, Xiaoyang Li, Yijia Luo, Zihe Liu, Ling Pan, Junchi Yan, Wei Wang, Wenbo Su, Jiamang Wang, Lin Qu, Bo Zheng

Taobao RL4LLM Technical Report, 2025
ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving

Han Lu*, Xiaosong Jia*, Yichen Xie, Wenlong Liao, Xiaokang Yang, Junchi Yan

CVPR 2026 (Highlight)
Sel4FT: Annotation Selection for Pretraining-Finetuning with Distribution Shift

Han Lu*, Yichen Xie*, Mingde Ding, Weizhong Zhan, Xiaokang Yang, Masayoshi Tomizuka, Junchi Yan

IEEE TPAMI, 2025
Rethinking Classifier Re-Training in Long-Tailed Recognition: Label Over-Smooth Can Balance

Siyu Sun*, Han Lu*, Jiangtong Li, Yichen Xie, Tianjiao Li, Xiaokang Yang, Liqing Zhang, Junchi Yan

ICLR 2025

Paper Code
Boundary Matters: A Bi-Level Active Finetuning Framework

Han Lu, Yichen Xie, Xiaokang Yang, Junchi Yan

NeurIPS 2024

Code
Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm

Yichen Xie, Han Lu, Xiaokang Yang, Junchi Yan

CVPR 2023
ROCO: A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on Graphs

Han Lu*, Zenan Li*, Runzhong Wang, Qibing Ren, Xijun Li, Mingxuan Yuan, Jia Zeng, Xiaokang Yang, Junchi Yan

ICLR 2023

Code
Yes or No: Active Learning with Binary Feedback for Efficient Label Acquisition

Han Lu, Chenhao Zhong, Haoran Ruan, Muyang Qian, Xiaojin Zuo, Linfang Shi

ICIC 2025 (Oral)
Learning-Aided Heuristics Design for Storage System

Yingtian Tang*, Han Lu*, Xijun Li, Lei Chen, Mingxuan Yuan, Jia Zeng

SIGMOD 2021
Continual Predictive Learning from Videos

Geng Chen, Wendong Zhang, Han Lu, Siyu Gao, Yunbo Wang, Mingsheng Long, Xiaokang Yang

CVPR 2022 (Oral)
Detailed 2D-3D Joint Representation for Human-Object Interaction

Yong-Lu Li, Xinpeng Liu, Han Lu, Siyuan Wang, Jingyi Liu, Jiefeng Li, Cewu Lu

CVPR 2020

Education

Shanghai Jiao Tong University

Ph.D. in Computer Science — Wu Wenjun AI Honors Class, advised by Prof. Junchi Yan

2021 – 2026

Shanghai Jiao Tong University

B.Eng. in Computer Science — Zhiyuan ACM Honors Class (Top 5%)

2017 – 2021

Jiangsu Changzhou Senior High School

NOI 2016 Silver Medal, APIO 2016 Gold Medal

2014 – 2017

Honors & Awards

NOI 2016 Silver Medal & APIO 2016 Gold Medal (Admitted to SJTU with national guarantee)
Huawei Hackathon 2024 — First Prize (only university team among 1000+ participants)
Zhiyuan Outstanding Student Scholarship (2021)
Zhiyuan Honors Scholarship (2018 – 2021)
Wu Wenjun Doctoral Honors Scholarship (2021 – 2025)
Huawei Noah's Ark Outstanding Intern Award (Top 20%)

Academic Service

Reviewer: NeurIPS, ICML, ICLR, CVPR, ICCV, AAAI, IJCAI, ACM MM, AISTATS
Teaching: Vice class advisor for SJTU ACM Class (Class of 2023); TA for Programming & Data Structures; Coach at Jiangsu Province Informatics Olympiad Winter Camp