Yue Wang
I am an Assistant Professor atUSC CS (2023 Fall-), leading theGeometry, Vision, and Learning Lab. I graduated from MIT EECS in 2022, advised byProf. Justin Solomon at theGeometric Data Processing Group. I was also fortunate to collaborate withProf. Michael Bronstein andProf. Phillip Isola. Previously, I was a master student at University of California, San Diego. Prior to that, I received my BEng in Computer Science from Zhejiang University.
My research lies in the intersection of computer vision, computer graphics, and robotics. My goal is to use machine learning toenable robotic intelligence with minimal human supervision. I study how to design 3D learning systems which leverage geometry, appearance, motion, and any other cues that are naturally available in sensory inputs. I am also broadly interested in fundamental deep learning tools and eclectic applications on top of these systems.
Topics I currently focus on include:
- Simulation. Constructing photorealistic simulations that replicate rare environments and enabling foundation model learning from synthetic or hybrid data sources.
- Perception. Leveraging geometric, semantic, and motional cues to develop data-efficient algorithms for robust scene perception and understanding in both simulated and real-world settings.
- Decision Making. Integrating knowledge from foundation models (such as LLMs) into intelligent agents to enhance autonomous decision-making capabilities in novel and unknown environments.
PhD students:
- Emily Jia (co-advised withYajie Zhao)
- Jiageng Mao (Qualcomm Fellow)
- Jiawei Yang (Nvidia Fellow, Annenberg Fellow)
- Junjie Ye (Qualcomm Fellow, Capital One Fellow)
- Cameron Smith
- Siheng Zhao
MS students:
Undergrads:
- Dylan Sun
Visitors:
- Ziyu Chen
Alumni:
- James Qian (Next stop: Stanford)
Selected Award:
- Toyota Research Young Faculty Researcher
- Powell Faculty Research Award
- ICBS Best Paper Award
- Nvidia Fellowship
- MIT William A. Martin Master’s Thesis Award
news
| Feb 11, 2025 | PhysBench is selected as an oral presentation (1.8%). OmniRe and LoRA3D are selected as spotlight presentations (5.1%). Congratulations to Wei, Jiageng, Ziyu, and Ziqi. |
|---|---|
| Jan 28, 2025 | Two papers accepted to ICRA 2025! Congratulations to Jiageng and Junjie. |
| Jan 22, 2025 | Eight papers accepted to ICLR 2025! Congratulations to all my students and collaborators. |
| Oct 1, 2024 | Serve as Area Chairs for 3DV 2025, ICLR 2025, CVPR 2025, and a Presentation Chair for RSS 2025. |
| Sep 25, 2024 | Three papers (including one spotlight) accepted to NeurIPS 2024. |
selected publications
@inproceedings{chow2025,title={PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding},author={Chow*, Wei and Mao*, Jiageng and Li, Boyi and Seita, Daniel and Guizilini, Vitor Campagnolo and Wang, Yue},year={2025},booktitle={International Conference on Learning Representations},}@inproceedings{chen2025,title={OmniRe: Omni Urban Scene Reconstruction},author={Chen, Ziyu and Yang, Jiawei and Huang, Jiahui and de Lutio, Riccardo and Esturo, Janick Martinez and Ivanovic, Boris and Litany, Or and Gojcic, Zan and Fidler, Sanja and Pavone, Marco and Song, Li and Wang, Yue},year={2025},booktitle={International Conference on Learning Representations},}@inproceedings{lu2025,title={LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation models},author={Lu, Ziqi and Yang, Heng and Xu, Danfei and Li, Boyi and Ivanovic, Boris and Pavone, Marco and Wang, Yue},year={2025},booktitle={International Conference on Learning Representations},}@inproceedings{yang2025,title={STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes},author={Yang, Jiawei and Huang, Jiahui and Chen, Yuxiao and Wang, Yan and Li, Boyi and You, Yurong and Sharma, Apoorva and Igl, Maximilian and Karkus, Peter and Xu, Danfei and Ivanovic, Boris and Wang*, Yue and Pavone*, Marco},year={2025},booktitle={International Conference on Learning Representations},}@inproceedings{kuang2024,title={RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation},author={Kuang, Yuxuan and Ye, Junjie and Geng, Haoran and Mao, Jiageng and Deng, Congyue and Guibas, Leonidas and Wang, He and Wang, Yue},year={2024},booktitle={The Conference on Robot Learning},}@inproceedings{mao2024agent,title={A Language Agent for Autonomous Driving},author={Mao*, Jiageng and Ye*, Junjie and Qian, Yuxi and Pavone, Marco and Wang, Yue},year={2024},booktitle={Conference on Language Modeling},}@inproceedings{yang2024dvt,title={Denoising Vision Transformers},author={Yang*, Jiawei and Luo*, Katie Z and Li, Jiefeng and Deng, Congyue and Guibas, Leo and Weinberger, Kilian Q and Tian, Yonglong and Wang, Yue},year={2024},booktitle={The European Conference on Computer Vision},}@inproceedings{yang2023emernerf,title={EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision},author={Yang, Jiawei and Ivanovic, Boris and Litany, Or and Weng, Xinshuo and Kim, Seung Wook and Li, Boyi and Che, Tong and Xu, Danfei and Fidler, Sanja and Pavone, Marco and Wang, Yue},year={2024},booktitle={International Conference on Learning Representations},}