Jing Zhang

Jing Zhang | 张婧

I'm a Faculty Fellow at the NYU Center for Robotics and Embodied Intelligence (CREO). Previously, I was a postdoctoral researcher at AI4CE Lab@NYU led by Prof. Chen Feng and Anthrotopography Lab@NYU led by Prof. Radu Iovita.

Over the next three years, I pursue two concrete goals: (1) building mobile agents that autonomously navigate New York City, use tools, and assist people safely; and (2) reassembling fractured fossils and artifacts to help reveal patterns of human evolution.

I advance these aims through Evolving Embodied Intelligence, a cognitively inspired framework that integrates perception, imagination, reasoning, action, and feedback in a closed loop across the physical and digital worlds.

I did my PhD (2023) in Photogrammetry and Remote Sensing from Wuhan University, under the guidance of Prof. Bin Luo and Prof. Yajun Wang. Before this, I received my B.E. degree (2017) and M.S. degree (2019) from Wuhan University.

I am on the job market for faculty and industry research positions.

I enjoy dancing in my spare time and dancing helps me to be energetic longer.

Email / Scholar / Twitter / LinkedIn

Research Highlights

Research Overview: Evolving Embodied Intelligence

Recent News

[09/2026] I have joined the NYU Center for Robotics and Embodied Intelligence (CREO) as a Faculty Fellow.

[09/2026] I am teaching a course on Mathematics for Robotics (ROB-GY 6013) during the Fall 2026 semester.

[02/2026] Our paper CRAG has been accepted to ICML 2026.

[02/2026] Our paper EgoPush is available on arXiv, with code and videos on the project page.

[02/2026] Our papers Wanderland (Highlight) and Thinking in 360° have been accepted to CVPR 2026.

[10/2025] I am the PI of the NYU Postdoctoral Research and Professional Development Grant–funded project Enabling Functional Dexterous In-Hand Reorientation for General-Purpose Robotic Manipulation.

[10/2025] I was honored to be selected as one of the MIT EECS Rising Stars 2025.

[8/2025] I serve as a Co-PI of the NSF-funded project DigitizedNYC: Large-Scale 4D Urban Digital Twin for Embodied AI (OAC), awarded $599,806.

[07/2025] I will be teaching a course on Robot Perception during the Fall 2025 semester.

[06/2025] Our papers GARF and RAP have been accepted to ICCV 2025.

[02/2025] Our paper CityWalker has been accepted to CVPR 2025.

[01/2025] Our paper FusionSense has been accepted to ICRA 2025.

[06/2024] I will be co-teaching a course on Robot Vision during the Spring 2025 semester.

[04/2024] Our paper LUWA has been accepted and selected as a highlight at CVPR 2024.

Recent Talks

[2026] Talk at the Voxel51 AI, ML and Computer Vision Meetup (upcoming).

[06/2025] Invited Talk at the CVPR 2025 Workshop.

[04/2025] Invited Talk at the Paleoanthropology Society 2025 Annual Meeting.

[01/2025] Invited Talk at the NYU Abu Dhabi Institute.

Selected Publications

^* Equal contribution. ^† Corresponding author.

	CRAG: Can 3D Generative Models Help 3D Assembly? Zeyu Jiang, Sihang Li, Siqi Tan, Chenyang Xu, Juexiao Zhang, Julia Galway-Witham, Xue Wang, Scott A. Williams, Radu Iovita, Chen Feng^†, Jing Zhang^† ICML, 2026 project page / arXiv Reformulating 3D assembly and generation as a mutually reinforcing joint problem.
	Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI Xinhao Liu, Jiaqi Li, Youming Deng, Ruxin Chen, Yingjia Zhang, Yifei Ma, Li Guo, Yiming Li, Jing Zhang^†, Chen Feng^† CVPR, 2026 (Highlight) project page / arXiv / github A geometrically grounded real-to-sim framework for open-world embodied AI.
	Thinking in 360°: Humanoid Visual Search in the Wild Heyang Yu, Yinan Han, Xiangyu Zhang, Baiqiao Yin, Bowen Chang, Xiangyu Han, Xinhao Liu, Jing Zhang, Marco Pavone, Chen Feng, Saining Xie, Yiming Li CVPR, 2026 project page / arXiv A humanoid agent that actively rotates its head to search a 360° immersive world.
	EgoPush: Learning End-to-End Egocentric Multi-Object Rearrangement for Mobile Robots Boyuan An, Zhexiong Wang^, Yipeng Wang^, Jiaqi Li, Sihang Li^†, Jing Zhang^†, Chen Feng^† arXiv, 2026 project page / arXiv Egocentric, map-free multi-object rearrangement: a mobile robot pushes objects into target formations from a single forward camera.
	GARF: Learning Generalizable 3D Reassembly for Real-World Fractures Sihang Li^, Zeyu Jiang^, Grace Chen, Chenyang Xu, Siqi Tan, Xue Wang, Irving Fang, Kristof Zyskowski, Shannon P. McPherron, Radu Iovita, Chen Feng^†, Jing Zhang^† ICCV, 2025 project page / arXiv / github Shedding light on training on synthetic data to advance real-world 3D fracture assembly.
	RAP: Unleashing the Power of Data Synthesis in Visual Localization Sihang Li^, Siqi Tan^, Bowen Chang, Jing Zhang, Chen Feng^†, Yiming Li^† ICCV, 2025 project page / arXiv / github Make camera localization more generalizable by addressing the data gap via 3DGS and learning gap via a two-branch joint learning with adversarial loss.
	FusionSense: Bridging Common Sense, Vision, and Touch for Robust Sparse-View Reconstruction Irving Fang^, Kairui Shi^, Xujin He^, Siqi Tan, Yifan Wang, Hanwen Zhao, Hung-Jui Huang, Wenzhen Yuan, Chen Feng^†, Jing Zhang^† ICRA*, 2025 project page / arXiv / github Helping robots fuse vision, touch, and common sense via 3DGS using sparse-view data.
	CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos Xinhao Liu^, Jintong Li^, Yicheng Jiang, Niranjan Sujay, Zhicheng Yang, Juexiao Zhang, John Abanes, Jing Zhang, Chen Feng^† CVPR, 2025 project page / arXiv / github Train autonomous agents for robust urban navigation using Internet-scale videos.
	LUWA Dataset: Learning Lithic Use-Wear Analysis on Microscopic Images Jing Zhang^, Irving Fang^, Hao Wu, Akshat Kaushik, Alice Rodriguez, Hanwen Zhao, Juexiao Zhang, Zhuo Zheng, Radu Iovita^†, Chen Feng^† CVPR, 2024 (Highlight) project page / arXiv / github Could Foundation Models uncover the hidden story of ancient tools? Creating the first open-source and largest Lithic Use-Wear Analysis (LUWA) dataset and challenge Large Vision Model and Large Language and Vision Model with it.
	Single-Exposure Optical Measurement of Highly Reflective Surfaces via Deep Sinusoidal Prior for Complex Equipment Production Jing Zhang, Bin Luo, Fuqian Li, Xingman Niu, Qican Zhang, Yajun Wang^† IEEE Transactions on Industrial Informatics, 2022 Could damaged phase be recovered without training samples for HDR 3D reconstruction? Designing deep sinusoidal prior (DSP) for damaged phase recovery.
	Superfast and Large-Depth-Range Sinusoidal Fringe Generation for Multi-Dimensional Information Sensing Sijie Zhu^, Zhoujie Wu^, Jing Zhang, Qican Zhang, Yajun Wang^† Photonics Research, 2022 video Building multifocal projection system for superfast and large-depth range 3D measurement.
	Deep-Learning-based Adaptive Camera Calibration for Various Defocusing Degrees Jing Zhang, Bin Luo, Zhuolong Xiang, Qican Zhang, Yajun Wang^†, Xin Su, Jun Liu, Lu Li, Wei Wang Optics Letters, 2021 (Highlighted as an Editor’s Pick) Improving camera calibration via target enhancement for high-fidelity 3D reconstruction.
	A Convenient 3D Reconstruction Model based on Parallel-Axis Structured Light System Jing Zhang, Bin Luo, Xin Su, Lu Li, Beiwen Li, Song Zhang, Yajun Wang^† Optics and Lasers in Engineering, 2021 Building a convenient parallel-axis structured light system to avoid shadow and occlusion.
	Depth Range Enhancement of Binary Defocusing Technique based on Multi-Frequency Phase Merging Jing Zhang, Bin Luo, Xin Su, Yuwei Wang, Xiangcheng Chen, Yajun Wang^† Optics Express, 2019 Proposing multi-frequency phase merging for depth range enhancement.
	High Dynamic Range 3D Measurement based on Spectral Modulation and Hyperspectral Imaging Yajun Wang, Jing Zhang, Bin Luo ^† Optics Express, 2018 Building a spectral modulation system for HDR 3D measurement.

Academic Service

Reviewer	Scientific Reports IEEE Robotics and Automation Letters (RA-L) PLOS Optics and Lasers in Engineering Optics Letters Optics Express ICRA, CVPR
Advisor	C.A.A.B. - CMML, Anthrotopography, AI4CE, and Bromage Labs, NYU Applied Research In Science and Engineering (ARISE). NYU Self Drive Team, NYU Multidisciplinary Undergraduate Vertically Integrated Project (VIP).

Source code from Jon Barron's website.

Research Highlights

Recent News

Recent Talks

Selected Publications

Academic Service

Website Visitors Map