Lei Li

Professor @ Beijing Institute of Technology北京理工大学教授

Contact Information联系方式

Beijing Institute of Technology (BIT), School of AI北京理工大学，人工智能学院

Deputy Director, Computational Intelligence Center认知智能研究中心副主任

State Key Lab of Autonomous Intelligent Unmanned Systems 自主智能无人系统全国重点实验室

lilei@bit.edu.cn

Research Focus研究方向

Large Multimodal/Language Models · MedicalAI · Embodied & Physical AI · AIGC多模态/语言模型 · 医疗AI · 具身与物理人工智能 · AIGC

Google Scholar LinkedIn X (Twitter) ResearchGate

Collaboration & Students招生合作

I am always looking for visiting scholars, Postdocs, PhD students, (remote) interns, and visiting students. 长期欢迎访问学者、博士后、博士生、远程实习生和访问学生加入团队。

I am always open to possible discussion and research collaboration with junior students. I value diversity and fresh perspectives in artificial intelligence research. 欢迎交流讨论与开展科研合作。团队重视多元背景，鼓励对人工智能研究有热情的同学联系。

Students from underrepresented groups are strongly encouraged to reach out!特别鼓励来自多元背景的学生主动联系！ If you are interested in working together, please contact me at 如有合作兴趣，请联系： lilei@bit.edu.cn.

Research Overview研究方向

Large Multimodal & Language Models (LMMs/LLMs):大型多模态与语言模型： Exploring unified representations across text, vision, audio, and 3D modalities. The focus is on cross-modal alignment, complex reasoning, and advancing foundational model architectures for comprehensive understanding. 文本、视觉、音频和三维等多模态的统一表征，重点关注跨模态对齐、复杂推理，以及面向综合理解的基础模型架构。

Embodied & Physical AI:具身与物理人工智能： Investigating AI perception and interaction within physical environments. Key areas include human and robotic representation learning, sensorimotor control, and grounding physical commonsense in multimodal models. 物理环境中的感知与交互，涵盖人类与机器人表征学习、感知运动控制，以及多模态模型中的物理常识 grounding。

Understanding & Generation (AIGC):理解与生成（AIGC）： Advancing Generative AI to create high-fidelity and controllable content. Research covers the generation of images, complex 3D scenes, dynamic videos, and interactive virtual humans. 生成式人工智能在高保真、可控内容生成中的应用，研究内容包括图像、复杂三维场景、动态视频和交互式虚拟人生成。

Cognitive Intelligence:认知智能： Explore foundational multimodal models to advance cognitive intelligence. This includes cross-modal reasoning in healthcare, cognitive decision support, and simulation. 探索面向认知智能的多模态基础模型，包括医疗场景中的跨模态推理、认知决策支持与仿真。

Current Priorities:近期重点： Large multimodal/language models for generation and cognitive understanding; Embodied and Physical AI; AIGC for 3D/video/human content; and multimodal AI into advanced cognitive health applications. 生成与认知理解的多模态模型、医疗AI、具身与物理人工智能、三维/视频/人物内容生成。

Academic Service学术服务

Committee Member, Multilingual Intelligent Information Processing Technical Committee, Chinese Association for Artificial Intelligence中国人工智能学会多语种智能信息处理专业委员会委员
Committee Member, Cognitive Modeling Technical Committee, Chinese Association for Cognitive Science中国认知科学学会认知建模专业委员会委员
Organization Chair, International Conference on Multilingual Intelligence多语种智能国际会议组织主席
Associate Editor, Data IntelligenceData Intelligence 副主编
Reviewer for journals including TPAMI, Information Fusion, and TMMTPAMI、Information Fusion、TMM 等期刊审稿人
Program Committee Member and Area Chair for conferences including CVPR, NeurIPS, ICLR, and AAAICVPR、NeurIPS、ICLR、AAAI 等会议程序委员会委员和分会主席
Lead instructor for courses including Introduction to Artificial Intelligence, Deep Learning, and Machine Learning主导讲授《人工智能导论》《深度学习》《机器学习》等课程

Recent Selected Publications代表性论文

Corresponding Author: *通讯作者：*

BCL: Bayesian In-Context Learning Framework for Information Extraction. Haoliang Liu, Chengkun Cai, Xu Zhao, Han Zhu, Shizhou Huang, Xinglin Zhang, Tao Chen, Jenq-Neng Hwang, Zhang Huaping, Lei Li*. ACL 2026

How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation. Hao Yang, Qinghua Zhao, Lei Li, Lingyi Meng, Mengda Yu. ACL 2026

Improving Multimodal Reasoning via Worst Dimension Optimization. Haocheng Lv, Huaping Zhang, Qiuchi Li, Lei Li, Chunxiao Gao. IJCAI 2026

Domain Adaptation for Speaker Verification Using Optimal Transport with Pseudo Label. Wenhao Yang, Jianguo Wei, Wenhuan Lu, Lei Li*, Xugang Lu. IEEE Transactions on Information Forensics and Security 2026

3D Gaussian Grounding for Enhanced Scene Understanding. Minling Zhu, Jiahua Yuan, Dongbing Gu, Maodong He, Zongkai Wu, Jiale Zhou, Lei Li*. Big Data Mining and Analytics 2026

Video Understanding: From Geometry and Semantics to Unified Models. Zhaochong An, Zirui Li, Mingqiao Ye, Feng Qiao, Jiaang Li, Zongwei Wu, Vishal Thengane, Chengzu Li, Lei Li, Van Gool Luc, Guolei Sun, Serge Belongie. Machine Intelligence Research 2026

Robust Multi-Domain Digital Pathology Image Segmentation via Joint Balancing Representation Learning. Qiaoyi Xu, Azizi Abdullah, Tao Chen, Xinglin Zhang, Adam Shephard, Patsy Ng Pei Sze, Noraidah Masir, Lei Li*, Reena Rahayu. Expert Systems With Applications 2026

Intrinsic Entropy of Context Length Scaling in LLMs. Jingzhe Shi, Qinwei Ma, Hongyi Liu, Hang Zhao, Jenq-Neng Hwang, Lei Li*. ICLR 2026 Oral

RAM: Recover Any 3D Human Motion in-the-Wild. Sen Jia, Ning Zhu, Jinqin Zhong, Jiale Zhou, Zhang Huaping, Jenq-Neng Hwang, Lei Li*. CVPR 2026

CLEP: Contrastive Language-Pose Pretraining. Sen Jia, Huayu Wang, Hsiang-Wei Huang, Zhaochong An, Jenq-Neng Hwang, Zhang Huaping, Lei Li*. CVPR 2026

Learning to Learn Weight Generation via Local Consistency Diffusion. Yunchuan Guan, Yu Liu, Ke Zhou, Zhiqi Shen, Jenq-Neng Hwang, Lei Li*. CVPR 2026

PSGS: Text-driven Panorama Sliding Scene Generation via Gaussian Splatting. Xin Zhang, Shen Chen, Jiale Zhou, Lei Li*. ICASSP 2026

CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications. Tianfang Zhang, Lei Li, Yang Zhou, Wentao Liu, Chen Qian, Jenq-Neng Hwang, Xiangyang Ji. IEEE TIP 2026

Multiple Human Motion Understanding. Lei Li*, Sen Jia, Jenq-Neng Hwang. AAAI 2026

3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting. Ziyang Yan, Yihua Shao, Minwen Liao, Siyu Chen, Nan Wang, Muyuan Lin, Jenq-Neng Hwang, Hao Zhao, Fabio Remondino, Lei Li*. WACV 2026

Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy. Yunchuan Guan, Yu Liu, Ke Zhou, Zhiqi Shen, Jenq-Neng Hwang, Serge Belongie, Lei Li*. ICCV 2025

AU-Blendshape for Fine-grained Stylized 3D Facial Expression Manipulation. Hao Li, Ju Dai, Feng Zhou, Kaida Ning, Lei Li, Junjun Pan. ICCV 2025

PAMN: Multi-phase Correlation Modeling for Contrast-Enhanced 3D Medical Image Retrieval. Haonan Tong, Ke Liu, Chuang Zhang, Xinglin Zhang, Tao Chen, Jenq-Neng Hwang, Lei Li*. EMNLP 2025

Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balance. Yunchuan Guan, Yu Liu, Ke Zhou, Hui Li, Sen Jia, Zhiqi Shen, Ziyang Wang, Xinglin Zhang, Tao Chen, Jenq-Neng Hwang, Lei Li*. ECAI 2025

Attention Consistency for LLMs Explanation. Tian Lan, Jinyuan Xu, Xue He, Jenq-Neng Hwang, Lei Li*. EMNLP 2025

MoCount: Motion-Based Repetitive Action Counting. Ruocheng Gu, Sen Jia, Yule Ma, Jinqin Zhong, Jenq-Neng Hwang, Lei Li*. ACMMM 2025

Graph Canvas for Controllable 3D Scene Generation. Libin Liu, Shen Chen, Sen Jia, Jingzhe Shi, Can Jin, Zongkai Wu, Jenq-Neng Hwang, Lei Li*. ACMMM 2025

Medal S: Spatio-Textual Prompt Model for Medical Segmentation. Pengcheng Shi, Jiawei Chen, Lei Li*. CVPR 2025

CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model. Ziyu Yao, Xuxin Cheng, Zhiqi Huang, Lei Li*. CVPR 2025

Human Motion Instruction Tuning. Lei Li*, Sen Jia, Jianhao Wang, Zhongyu Jiang, Feng Zhou, Ju Dai, Tianfang Zhang, Zongkai Wu, Jenq-Neng Hwang. CVPR 2025

Bayesian Optimization for Controlled Image Editing via LLMs. Chengkun Cai, Haoliang Liu, Xu Zhao, Zhongyu Jiang, Tianfang Zhang, Zongkai Wu, John Lee, Jenq-Neng Hwang, Lei Li*. ACL 2025

The Role of Deductive and Inductive Reasoning in LLMs. Chengkun Cai, Xu Zhao, Haoliang Liu, Zhongyu Jiang, Tianfang Zhang, Zongkai Wu, Jenq-Neng Hwang, Lei Li*. ACL 2025

In-Context Meta LoRA Generation. Yihua Shao, Minxi Yan, Yang Liu, Siyu Chen, Wenjie Chen, Xinwei Long, Ziyang Yan, Lei Li, Nicu Sebe, Hao Tang, Yan Wang, Hao Zhao, Mengzhu Wang, Jingcai Guo. IJCAI 2025

UniHPR: Unified Human Pose Representation via Singular Value Contrastive Learning. Zhongyu Jiang, Wenhao Chai, Lei Li*, Zhuoran Zhou, Cheng-Yen Yang, Jenq-Neng Hwang. MIPR 2025 (Best Paper)

You Only Speak Once to See. Wenhao Yang, Jianguo Wei, Wenhuan Lu, Lei Li. ICASSP 2025

Scaling Law for Time Series Forecasting. Jingzhe Shi, Qinwei Ma, Huan Ma, Lei Li*. NeurIPS 2024

CHOPS: CHat with custOmer Profile Systems for Customer Service with LLMs. Jingzhe Shi, Jialuo Li, Lei Li*. COLM 2024

Image Semantic Segmentation via Chain-of-Thought Prompts. Lei Li. WACV 2024

Back to Optimization: Diffusion-based Zero-shot 3D Human Pose Estimation. Zhongyu Jiang, Lei Li*, Jenq-Neng Hwang. WACV 2024

Deep Point Cloud Regression for Above-ground Forest Biomass Estimation. Stefan Oehmcke, Lei Li#, Christian Igel. Remote Sensing of Environment 2024