职称：准聘教授
E-mail：lilei@ustc.edu
通信地址：北京市海淀区中关村南大街5号院人工智能学院认知智能实验室（104）
基本情况
李磊，博士，北京理工大学人工智能学院准聘教授，博士生导师，特立学者。2026年3月加入北京理工大学人工智能学院，主要研究方向为多模态,生成模型,机器学习等。多年在哥本哈根大学，华盛顿大学等从事人工智能和多模态领域的研究，与斯坦福大学，卡耐基梅隆大学，瑞士联邦理工大学，牛津大学有深入的交流和合作，取得了一系列具有国际影响力的成果。以第一作者或通讯作者身份发表顶级论文 40余篇（如 CVPR, NeurIPS，ACL，ICLR）。在CVPR挑战赛荣获荣誉提名奖，在MIPR，ICCC等国际会议荣获最佳论文奖，于AAAI，CVPR，NeruIPS等会议分会主席和程序委员会。
每年计划招生博士生1人，硕士研究生3-4人，同时欢迎高年级优秀本科生加入课题组。
个人主页：
https://xunuo212.github.io/LiLei.html
研究方向
多模态模型，生成模型，具身智能，自然语言处理，信息检索，人工智能，大语言模型
主要获奖情况
(1) 最佳论文奖，UniHPR: Unified Human Pose Representation via Singular Value Contrastive Learning。该论文在 2025年第八届 IEEE 多媒体信息处理与检索国际会议 (MIPR 2025) 中获得最佳论文奖。
(2) 荣誉提名奖 (Honorable Mention)，2025年 CVPR (IEEE/CVF 计算机视觉与模式识别会议) challenge。获奖作品为：Medal S: Spatio-Textual Prompt Model for Medical Segmentation。
(3) 最佳论文奖，2022年第八届 IEEE 计算机与通信国际会议 (ICCC 2022)。获奖论文：LR-CSNet: Low-rank deep unfolding network for image compressive sensing。
代表性论文
[1] Jingzhe Shi, Qinwei Ma, Hongyi Liu, Hang Zhao, Jenq-Neng Hwang, Lei Li*. “Intrinsic Entropy of Context Length Scaling in LLMs”. International Conference on Learning Representations (ICLR) 2026,(oral).
[2] Sen Jia, Ning Zhu, Jinqin Zhong, Jiale Zhou, Zhang Huaping, Jenq-Neng Hwang, Lei Li*. “RAM: Recover Any 3D Human Motion in-the-Wild”. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026.
[3] Sen Jia, Huayu Wang, Hsiang-Wei Huang, Zhaochong An, Jenq-Neng Hwang, Zhang Huaping, Lei Li*. “CLEP: Contrastive Language-Pose Pretraining”. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026.
[4] Yunchuan Guan, Yu Liu, Ke Zhou, Zhiqi Shen, Jenq-Neng Hwang, Lei Li*. “Learning to Learn Weight Generation via Local Consistency Diffusion”. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026.
[5] Xin Zhang, Shen Chen, Jiale Zhou, Lei Li*. “PSGS: Text-driven Panorama Sliding Scene Generation via Gaussian Splatting”. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2026.
[6] Lei Li*, Sen Jia, Jenq-Neng Hwang. “Multiple Human Motion Understanding”. AAAI Conference on Artificial Intelligence (AAAI) 2026.
[7] Qiaoyi Xu, Azizi Abdullah, Tao Chen, Xinglin Zhang, Adam Shephard, Patsy Ng Pei Sze, Noraidah Masir, Lei Li*, Reena Rahayu. “Robust Multi-Domain Digital Pathology Image Segmentation via Joint Balancing Representation Learning”. Expert Systems With Applications 2026.
[8] Ziyang Yan, Yihua Shao, Minwen Liao, Siyu Chen, Nan Wang, Muyuan Lin, Jenq-Neng Hwang, Hao Zhao, Fabio Remondino, Lei Li*. “3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting”. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2026.
[9] Yunchuan Guan, Yu Liu, Ke Zhou, Zhiqi Shen, Jenq-Neng Hwang, Serge Belongie, Lei Li*. “Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy”. International Conference on Computer Vision (ICCV) 2025.
[10] Haonan Tong, Ke Liu, Chuang Zhang, Xinglin Zhang, Tao Chen, Jenq-Neng Hwang, Lei Li*. “PAMN: Multi-phase Correlation Modeling for Contrast-Enhanced 3D Medical Image Retrieval”. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2025.
[11] Yunchuan Guan, Yu Liu, Ke Zhou, Hui Li, Sen Jia, Zhiqi Shen, Ziyang Wang, Xinglin Zhang, Tao Chen, Jenq-Neng Hwang, Lei Li*. “Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balance”. European Conference on Artificial Intelligence (ECAI) 2025.
[12] Tian Lan, Jinyuan Xu, Xue He, Jenq-Neng Hwang, Lei Li*. “Attention Consistency for LLMs Explanation”. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2025.
[13] Ruocheng Gu, Sen Jia, Yule Ma, Jinqin Zhong, Jenq-Neng Hwang, Lei Li*. “MoCount: Motion-Based Repetitive Action Counting”. ACM International Conference on Multimedia (ACMMM) 2025.
[14] Libin Liu, Shen Chen, Sen Jia, Jingzhe Shi, Can Jin, Zongkai Wu, Jenq-Neng Hwang, Lei Li*. “Graph Canvas for Controllable 3D Scene Generation”. ACM International Conference on Multimedia (ACMMM) 2025.
[15] Pengcheng Shi, Jiawei Chen, Jiaqi Liu, Xinglin Zhang, Tao Chen, Lei Li*. “Medal S: Spatio-Textual Prompt Model for Medical Segmentation”. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025.
[16] Ziyu Yao, Xuxin Cheng, Zhiqi Huang, Lei Li*. “CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model”. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025.
[17] Lei Li*, Sen Jia, Jianhao Wang, Zhongyu Jiang, Feng Zhou, Ju Dai, Tianfang Zhang, Zongkai Wu, Jenq-Neng Hwang. “Human Motion Instruction Tuning”. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025.
[18] Chengkun Cai, Haoliang Liu, Xu Zhao, Zhongyu Jiang, Tianfang Zhang, Zongkai Wu, John Lee, Jenq-Neng Hwang, Lei Li*. “Bayesian Optimization for Controlled Image Editing via LLMs”. Annual Meeting of the Association for Computational Linguistics (ACL) 2025.
[19] Chengkun Cai, Xu Zhao, Haoliang Liu, Zhongyu Jiang, Tianfang Zhang, Zongkai Wu, Jenq-Neng Hwang, Lei Li*. “The Role of Deductive and Inductive Reasoning in LLMs”. Annual Meeting of the Association for Computational Linguistics (ACL) 2025.
[20] Zhongyu Jiang, Wenhao Chai, Lei Li*, Zhuoran Zhou, Cheng-Yen Yang, Jenq-Neng Hwang. “UniHPR: Unified Human Pose Representation via Singular Value Contrastive Learning”. IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) 2025 (Best Paper).
[21] Chengbo Sun, Hui Yi Leong, Lei Li*. “Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports”. ICML 2025 Workshop.
[22] Jinyuan Xu, Tian Lan, Mathieu Valette, Pierre Magistry, Lei Li*. “TinyMentalLLMs Enable Depression Detection in Chinese Social Media Texts”. Recent Advances in Natural Language Processing (RANLP) 2025.
[23] Pengcheng Shi, Jiawei Chen, Jiaqi Liu, Xinglin Zhang, Tao Chen, Lei Li*. “Medal S: Spatio-Textual Prompt Model for Medical Segmentation”. CVPR 2025 Workshop (Honorable Mention).
[24] Wenhao Yang, Jianguo Wei, Wenhuan Lu, Lei Li*. “You Only Speak Once to See”. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2025.
[25] Shan Chen, Jiale Zhou, Lei Li*. “Dense Point Clouds Matter: Dust-GS for Scene Reconstruction from Sparse Viewpoints”. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2025.
[26] Youjia Fu, Zihao Xu, Junsong Fu, Huixia Xue, Shuqiu Tan, Lei Li*, Shaoxun Qing. “MonoMM: A Multi-scale Mamba-Enhanced Network for Real-time Monocular 3D Object Detection”. The Journal of Supercomputing 2025.
[27] Lei Li*, Xinglin Zhang, Jun Liang, Huang Mengqian, Tao Chen. “Addressing Domain Shift via Imbalance-Aware Domain Adaptation in Embryo Development Assessment”. Mathematical Biosciences and Engineering 2025.
[28] Jingzhe Shi, Qinwei Ma, Huan Ma, Lei Li*. “Scaling Law for Time Series Forecasting”. Neural Information Processing Systems (NeurIPS) 2024.
[29] Jingzhe Shi, Jialuo Li, Qinwei Ma, Zaiwen Yang, Huan Ma, Lei Li*. “CHOPS: CHat with custOmer Profile Systems for Customer Service with LLMs”. Conference on Language Modeling (COLM) 2024.
[30] Stefan Oehmcke, Lei Li$^#$, Katerina Trepekli, Jaime C. Revenga, Thomas Nord-Larsen, Fabian Gieseke, Christian Igel. “Deep Point Cloud Regression for Above-ground Forest Biomass Estimation from Airborne LiDAR”. Remote Sensing of Environment 2024.
[31] Lei Li. “Image Semantic Segmentation via Chain-of-Thought Prompts”. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024.
[32] Zhongyu Jiang, Zhuoran Zhou, Lei Li*, Wenhao Chai, Cheng-Yen Yang, Jenq-Neng Hwang. “Back to Optimization: Diffusion-based Zero-shot 3D Human Pose Estimation”. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024.
[33] Zhuoran Zhou, Zhongyu Jiang, Wenhao Chai, Cheng-Yen Yang, Lei Li*, Jenq-Neng Hwang. “Efficient Domain Adaptation via Generative Prior for 3D Infant Pose Estimation”. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024.
[34] Tianfang Zhang, Lei Li$^#$, Zhenming Peng. “Optimization-inspired Cumulative Transmission Network for Image Compressive Sensing”. Knowledge-Based Systems 2023.
[38] Tianfang Zhang, Lei Li$^#$, Christian Igel, Stefan Oehmcke, Fabian Gieseke, Zhenming Peng. “LR-CSNet: Low-rank Deep Unfolding Network for Image Compressive Sensing”. IEEE International Conference on Computer and Communications (ICCC) 2022 (Best Paper).
[39] Stefan Oehmcke, Lei Li*, Jaime C Revenga, Thomas Nord-Larsen, Katerina Trepekli, Fabian Gieseke, Christian Igel. “Deep Learning Based 3D Point Cloud Regression for Estimating Forest Biomass”. ACM SIGSPATIAL 2022.
主持参与科研项目
(1) 丹麦先锋人工智能中心 (Pioneer Centre for AI)，哥本哈根大学 (UCPH) 战略规划，丹麦国家研究基金会 (DNRF) 拨款编号 P1，“先锋人工智能中心” 2021-01 至 2034-12
(2) 新加坡研究院与企业联合资助项目，研究课题，无，“基于人工智能的 3D 运动范围与力量评估” 2025-10 至 2026-09，
(3) SKAI Intelligence，“3D 场景生成与仿真”，无，“3D 场景生成与仿真” 2024-12 至 2025-06
(4) Villum 基金会，“深度学习与遥感技术：解锁全球生态系统资源”，项目编号 34306，DeReEco 2021-01 至 2024-06，
获得的专利
[1] 钟金琴；辜若城；梁政；李磊；贾森；一种基于运动的人体动作重复计数方法及设备。
[2] 李磊；刘庭皓；王权；钱晨；关键点检测方法及装置、电子设备和存储介质。
教学工作
机器学习导论
人工智能导论
大数据技术