Jihan Yang

Member of Technical Staff @ AMI Labs

jihanyang13 [at] gmail [dot] com

jihan.yang [at] amilabs [dot] xyz

[Google Scholar]   [GitHub]   [Twitter]   [Linkedin]  

Biography


I am a founding scientist at AMI Labs. Before that, I was a postdoctoral fellow at NYU Courant, working with Prof. Saining Xie. I received my Ph.D degree from The University of Hong Kong, advised by Prof. Xiaojuan Qi. Prior to that, I obtained my Bachelor's degree from Sun Yat-sen University.

My research interests lie in machine learning and computer vision, focusing on world modeling and multimodal learning.

Selected Projects [Google Scholar]


*: Equal Contribution

Cambrian-S: Towards Spatial Supersensing in Video
Shusheng Yang*, Jihan Yang*, Pinzhi Huang, Ellis Brown, Zihao Yang, Yue Yu, Shengbang Tong, Zihan Zheng, Yifan Xu, Muhan Wang, Daohan Lu, Rob Fergus, Yann LeCun, Li Fei-Fei, Saining Xie
International Conference on Learning Representations (ICLR), 2026
[PDF] [BLOG] [CODE]GitHub stars [DATA] [MODEL] [BENCH]






Benchmark Designers Should “Train on the Test Set” to Expose Exploitable Non-Visual Shortcuts
Ellis Brown, Jihan Yang, Shusheng Yang, Rob Fergus, Saining Xie
arXiv preprint arXiv:2511.04655, 2025
[PDF] [BLOG] [CODE]GitHub stars [BENCH] [DATA]




UniTok: A Unified Tokenizer for Visual Generation and Understanding
Chuofan Ma, Yi Jiang, Junfeng Wu, Jihan Yang, Xin Yu, Zehuan Yuan, Bingyue Peng, Xiaojuan Qi
Advances in Neural Information Processing Systems (NeurIPS) 2025. [Spotlight]
[PDF] [BLOG] [CODE]GitHub stars




SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Tianzhe Chu*, Yuexiang Zhai*, Jihan Yang, Shengbang Tong, Saining Xie, Dale Schuurmans, Quoc V. Le, Sergey Levine, Yi Ma

International Conference on Machine Learning (ICML), 2025
[PDF] [BLOG] [CODE]GitHub stars [DATA]




Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces
Jihan Yang*, Shusheng Yang*, Anjali W. Gupta*, Rilyn Han*, Li Fei-Fei, Saining Xie.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025 [Oral]
[PDF] [BLOG] [CODE]GitHub stars [BENCH]




Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
Shengbang Tong*, Ellis Brown*, Penghao Wu*, Sanghyun Woo, Manoj Middepogu, Sai Charitha Akula, Jihan Yang, Shusheng Yang, Adithya Iyer, Xichen Pan, Austin Wang, Rob Fergus, Yann LeCun, Saining Xie.

Advances in Neural Information Processing Systems (NeurIPS) 2024. [Oral]
[PDF] [BLOG] [CODE]GitHub stars





V-IRL: Grounding Virtual Intelligence in Real Life
Jihan Yang, Runyu Ding, Ellis Brown, Xiaojuan Qi, Saining Xie.

European Conference on Computer Vision (ECCV), 2024.
[PDF] [BLOG] [CODE]GitHub stars


RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding
Jihan Yang*, Runyu Ding*, Weipeng Deng, Zhe Wang, Xiaojuan Qi.

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
[PDF] [BLOG] [CODE]GitHub stars





PLA: Language-driven Open-Vocabulary 3D Scene Understanding
Runyu Ding*, Jihan Yang*, Chuhui Xue, Wenqing Zhang, Song Bai, Xiaojuan Qi.

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[PDF] [BLOG] [CODE]GitHub stars




OpenPCDet: An Open-source Toolbox for 3D Object Detection from Point Cloud
OpenPCDet Development Team (2nd Core Developer)
[CODE] GitHub stars



Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation
Ruijia Xu, Guanbin Li, Jihan Yang, Liang Lin

IEEE International Conference on Computer Vision (ICCV), 2019.[Oral]
Best Paper Award Nomination (one of the seven among 1,075 accepted papers) refer to here.
[PDF] [CODE] GitHub stars





Experience


Invited Talks


2025/10: Invited talk @ Spatial Intelligence Seminar, Shanghai AI Lab Towards Spatial Supersensing
2025/09: Invited talk @ Twelve Labs Thinking in Space
2025/06: Invited talk @ University of Hong Kong Thinking in Space
2025/04: Invited talk @ University of Washington, NeuroAI Shlizerman Lab Thinking in Space
2025/03: Invited talk @ Johns Hopkins University, CCVL Research Group Thinking in Space
2025/02: Invited talk @ Bytedance, Seed Team Thinking in Space and SFTvsRL

Honors & Awards


2nd place on 3D detection, 3D tracking and domain adaptation three tracks of Waymo Open Challenges 2020
Postgraduate Scholarship, HKU 2020 - 2024
Best Paper Nomination, IEEE International Conference on Computer Vision (0.2%) 2019
Excellent Graduate Award of Sun Yat-sen University (2%) 2019
Excellent Dissertations of Sun Yat-sen University (2%) 2019
First Prize Scholarship of Sun Yat-sen University (4%) 2017, 2018

Academic Services


Conference Reviewer: Journal Reviewer:

Teaching


ELEC3249 Pattern Recognition and Machine Intelligence2022-2023
ENGG1310 Electricity and Electronics2021-2022
ELEC3249 Pattern Recognition and Machine Intelligence2020-2021