Jiageng Liu

Jiageng Liu (刘家耕)

I am a Ph.D. student in the Mobility Lab at University of California, Los Angeles (UCLA), advised by Prof. Jiaqi Ma.

Previously, I received my M.S. in Computer Science from University of Massachusetts Amherst, where I worked closely with Prof. Ming-Hsuan Yang at UC Merced.

Before that, I received my Bachelor's degree in Artificial Intelligence from the Turing Class, Chu Kochen Honors College & College of Computer Science and Technology, Zhejiang University, advised by Prof. Zhou Zhao.

My research interests lie in Embodied AI and Computer Vision.

Email: jiagengliu02@g.ucla.edu
CV / Google Scholar / Github / Linkedin

The photo was taken in ZJU for my graduation.

News

[2026.05] Started my Ph.D. in the Mobility Lab at UCLA.
[2026.01] One paper was accepted to ICLR 2026.
[2025.12] Started a research internship at Honda Research Institute USA.
[2025.09] One paper was accepted to NeurIPS 2025.

Show/Hide old news

[2024.10] One paper was accepted to NeurIPS 2024.
[2024.09] Started my M.S. in CICS at UMass Amherst.
[2024.03] One paper was accepted to CVPR 2024.
[2023.12] Received the National Scholarship in China.
[2023.09] One paper was accepted to NeurIPS 2023.
[2023.06] Joined MIT-IBM Watson AI Lab as an intern.
[2022.06] I had the honor of starring in the promotional video of Zhejiang University.

Research

My research focuses on embodied AI, spatial intelligence, and multimodal world modeling. I study how agents perceive, reason, and act in complex 3D environments, with interests in vision-language models, generative simulation, 3D scene understanding and editing, and test-time reasoning. More broadly, I aim to build interactive systems that tightly couple perception, memory, and action.

	ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop Preprint, 2026 Yining Hong, Jiageng Liu, Han Yin, Manling Li, Leonidas Guibas, Fei-Fei Li, Jiajun Wu, Yejin Choi [pdf] [web] [code] [dataset] [bibtex]
	Do Joint Audio-Video Generation Models Understand Physics? Preprint, 2026 Zijun Cui, Xiulong Liu, Hao Fang, Mingwei Xu, Jiageng Liu, et al.* [pdf] [web] [code] [dataset] [bibtex]
	LSM-VLM: Long-Short Memory VLM with World-Model for 3D Spatial Reasoning Preprint, 2026 Jiageng Liu, Nirav Savaliya, Faizan Siddiqui, Sahith Reddy Chada, Enna Sachdeva [pdf] [bibtex]
	Edit3r: Instant 3D Scene Editing from Sparse Unposed Images Jiageng Liu, Weijie Lyu, Xueting Li, Yejie Guo, Ming-Hsuan Yang [pdf] [web] [bibtex]
	Virtual Community: An Open World for Humans, Robots, and Society ICLR 2026 Qinhong Zhou, Jiageng Liu, and collaborators* [pdf] [web]
	MindJourney: Test-Time Scaling with World Models for Spatial Reasoning NeurIPS 2025 (Poster) Yuncong Yang, Jiageng Liu, Zheyuan Zhang, et al. [pdf] [web] [bibtex]
	ARCHITECT: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting NeurIPS 2024 (Poster) Yian Wang, Xiaowen Qiu, Jiageng Liu, et al.* [pdf] [web] [bibtex]
	RILA: Reflective and Imaginative Language Agent for Zero-Shot Semantic Audio-Visual Navigation CVPR 2024 (Poster) Zeyuan Yang, Jiageng Liu, Peihao Chen, et al. [pdf] [web] [bibtex]
	Connecting Multi-modal Contrastive Representations NeurIPS 2023 (Poster) Zehan Wang, Yang Zhao, Xize Cheng, Haifeng Huang, Jiageng Liu, Li Tang, Linjun Li, et al. [pdf] [web] [bibtex]
	WordDiffuser: Helping Beginners Cognize and Memorize Glyph-semantic Pairs Using Diffusion ISCID 2023 Yuhang Xu, Wanxu Xia, Yipeng Chen, Jiageng Liu, et al. [pdf] [bibtex]

Academic Service

Conference Reviewer: NeurIPS 2025, NeurIPS 2026, CVPR 2026
Journal Reviewer: IEEE Open Journal of Intelligent Transportation Systems

Experience

2025.12 - Present	Research Intern, Honda Research Institute USA Multi-modal scene representation and navigation in Habitat; Advisor: Nirav Savaliya.
2025.06 - 2025.11	Research Leader, Vision and Learning Lab, UC Merced Led Edit3r on instant 3D scene editing from sparse, unposed images; Advisor: Ming-Hsuan Yang.
2025.02 - 2025.06	Research Leader, Microsoft Research MindJourney: Test-time scaling with controllable world models for 3D spatial reasoning; Advisor: Jianwei Yang.
2023.11 - 2024.06	Research Leader, MIT-IBM Watson AI Lab ARCHITECT and RILA for 3D scene generation and audio-visual navigation;

Education

2026.05 - Present	Ph.D. in Civil and Environmental Engineering, UCLA Mobility Lab; advised by Jiaqi Ma.
2024.09 - 2025.12	M.S. in Computer Science, University of Massachusetts Amherst College of Information and Computer Sciences (GPA: 4.00/4.00).
2020.09 - 2024.07	B.S. in Artificial Intelligence, Zhejiang University Turing Class, Chu Kochen Honors College; GPA: 3.75/4.00 (Major GPA 3.96/4.00).

Last update: May. 2026

Thanks to Jon Barron for providing this amazing template.