Weize Li

Student Researcher
@ Lightillusions
@ AIR, Tsinghua University
Beijing, China
liweize0224@gmail.com

About Me

I am currently a student researcher at Lightillusions Robotics Team and Institute for AI Industry Research (AIR), Tsinghua University. I am fortunate to work closely with Prof. Ping Tan from HKUST, Dr. Xiaoxiao Long from HKU, and Prof. Hao Zhao from DISCOVER Lab. Previously, I was a visiting student at Institute of Automation, Chinese Academy of Sciences in my senior year. And I got my B.Eng. in Mechatronics Engineering from Beijing University of Civil Engineering and Architecture.

I am an active member of AnySyn3D, a non-profit research interest group comprising individuals with a strong interest in exploring research problems and cutting-edge technologies in any topics of 3D.

I am actively looking for the Ph.D. opportunity in Fall 2025.

Research

My long-term research goal is to build Embodied Intelligent Systems that connect Humans👫- Machines🤖 - Real World🌏 by perception, simulation, and interaction. I believe the key lies in leveraging human language🗣️ to help robots use 3D visual information to learn how to perceive, reason, and manipulate in both virtual and real world.
So I am currently focusing on {3D Vision, Robotics, Graphics} for Embodied AI:

👀3D Vision for Embodied Perception
3D Scene Understanding; 3D Vision-Language Model (e.g.grounding, dense captioning, VQA); ~~Anomaly Detection~~.
🤖Robotics for Embodied Interaction
Multi-task Manipulation; Long-horizon Mobile Manipulation; Autonomous Driving.
🪅Graphics for Embodied Simulation
3D Reconstruction and Editing, Video Generation.

Publications

(†: corresponding author; *: equal contribution)

ProGEM: Probing Generalizable and Efficient Feature Fields Distillation for Multi-Task Robotic Manipulation
Weize Li, Zhen Chen, Robin Ananda, Binxu Wu, Qi Lu, Qianyao Xu, Jiaying Li, Yingqing Xu.
CVPR 2025 Submission
[Coming Soon]

SCA-WM: Structure-aware Collaboratively Aligned World Model
Bu Jin^*, Zhenxin Zhu^*, Baihan Yang^*, Weize Li, Junpeng Jiang, Huan-ang Gao, Haiyang Sun, Kun Zhan, Peng Jia, Hao Zhao.
ICRA 2025 Submission
[Coming Soon]

Radiance Field-Based 3D Editing: A Survey
Weize Li^*, Tianshu Kuai^*, Huan-ang Gao, Xiangyue Liu, Yuhang Zheng, Yupeng Zheng, etc.
T-PAMI 2024 Submission
[arXiv] [Website]

TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes
Bu Jin, Yupeng Zheng^†, Pengfei Li, Weize Li, Yuhang Zheng, Sujie Hu, Xinyu Liu, Jinwei Zhu, Zhijie Yan, Haiyang Sun, Kun Zhan, Peng Jia, Xiaoxiao Long, Yilun Chen, Hao Zhao.
ECCV 2024 (Poster)
[arXiv] [Code]
[Special Ack. to Dave Zhenyu Chen@TUM for valuable proofreading and insightful suggestions.]

PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection
Weize Li^*, Qiang Zhou^*, Lihan Jiang, Guoliang Wang, Guyue Zhou, Shanghang Zhang, Hao Zhao.
NeurIPS 2023 Dataset and Benchmark Track (Poster)
[arXiv] [OpenReview] [Code]

IRFLMDNN: Hybrid Model for PMU Data Anomaly Detection and Re-filling with Improved Random Forest and Levenberg Marquardt Algorithm Optimized Dynamic Neural Network
Miao Yu^†, Chenyu Yang^*, Weize Li^*, Weijie Du, Jinglin Li.
Neural Computing and Application 2023
[Paper]

Projects

Zero1-to-Car: Finetuning Zero1-to-3 for Single Vehicle Image to 3D Generation
AIR Research Project 2023
[Coming soon]

McADTR: Multi-class Anomaly Detection TRansformer with Heterogenous Knowledge Distillation
AIR Summer Research 2022
[Code]

Patents (click to show all)

Awards

[2022] Best Undergraduate Dissertation Award, Beijing Education Commission (top 1% in 130,000 students).
[2022] Silver Award, Beijing Challenge Cup: Entrepreneurial Plan Competition in AI System Track (Rank.2)

Service

I served / was delegated as Reviewer for NeurIPS’23, CVPR’24, IJCV.

Misc.

Outside of research, I enjoy playing football⚽, fitness💪 and photography📷. I am a member of the Certified Referee of the Chinese Football Association. I am also a big fan of Taylor Swift🦋.

Meet our workmates: