I am interested in physical AI, spanning computer vision, computational sensing, AI agents and robotics.
Previously, my master's research focused on physics-based vision and imaging, and my undergraduate research explored generative models.
I am a first-year graduate student at MIT, working with Prof. Ramesh Raskar.
I obtained my M.S. in Robotics from Carnegie Mellon University,
where I was fortunate to be advised by Prof. Srinivasa Narasimhan and Prof. Aswin Sankaranarayanan.
Prior to that, I earned my B.E. in Computer Science with
the highest honor
from Zhejiang University.
×
![Enlarged view]()
VT-Intrinsic: Physics-Based Decomposition of Reflectance and Shading using a Single Visible-Thermal
Image Pair
Zeqing Yuan,
Mani Ramanagopal,
Aswin Sankaranarayanan,
Srinivasa Narasimhan
TLDR
Light absorbed rather than reflected leaves thermal traces that reveal
photometric image intrinsics.
Deep-Learning-Enabled Array Microscope with Extended Depth of Field for High-Throughput Slide-Free Pathology
Jimin Wu*, Huayu Hou*,
Zeqing Yuan,
Bakai Sheyitov, Angelina Yang, Junzhe Wang, Jinyun Liu, Mark Harfouche, Xiangjiang Bao, Sahar Sadeghi, Thomas Williams, Jennifer Carns, Richard A. Schwarz, Tomasz S. Tkaczyk, Ann M. Gillenwater, Ana Paula Refinetti, Lei Huo, Michelle D. Williams, Aswin C. Sankaranarayanan, Srinivasa G. Narasimhan, Roarke Horstmeyer, Ashok Veeraraghavan*, Rebecca R. Richards-Kortum*
TLDR
A computational array microscope with AI for rapid pathological guidance during tumor surgery.
Revealing Subtle Heat Flows all around us using Microbolometric Videos
Mani
Ramanagopal,
Akihiko Oharazawa,
Sriram Narayanan,
Zeqing Yuan,
Srinivasa Narasimhan
TLDR
Denoising thermal videos by modeling bolometric sensor physics.
FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior
Zhekai Chen*,
Wen Wang*,
Zhen Yang,
Zeqing Yuan,
Hao Chen,
Chunhua Shen
TLDR
Exploiting pretrained diffusion priors for zero-shot image composition.
SinLayout: Learning Generative 3D Scene Layouts from a Single Image
Zeqing Yuan*,
Linan Zhao*,
Yunzhi Zhang,
Shangzhe Wu,
Jiajun Wu
TLDR
Learning 3D spatial layout distribution from a single image using an adversarial generator.
ViSTec: Video Modeling for Sports Technique Recognition and Tactical Analysis
Zeqing Yuan*,
Yuchen He*,
Yihong Wu,
Liqi Cheng,
Dazhen Deng,
Yingcai Wu
TLDR
Parsing broadcast racket-sport videos into stroke-level technique sequences.
3D-PreMise: Can Large Language Models Generate 3D Shapes with Sharp Features and Parametric Control?
Zeqing Yuan*,
Haoxuan Lan*,
Qiang Zou,
Junbo Zhao
TLDR
Integrating LLMs with program synthesis in Blender and multi-modal CoT for parametric 3D modeling.
TIVEE: Visual Exploration and Explanation of Badminton Tactics in Immersive Visualizations
Xiangtong Chu,
Xiao Xie,
Shuainan Ye,
Haolin Lu,
Hongguang Xiao,
Zeqing Yuan,
Zhutian Chen,
Yingcai Wu
TLDR
Immersive VR visualization system for badminton tactical analysis.
No publications in this category yet.
Selected Honors
Columbia University Presidential Fellowship, 2026
Berkeley EECS Department Fellowship, 2026
Best Poster Award, CVPR Workshop on Computational Cameras and Displays, 2025
Chinese National Scholarship, Ministry of Education, 2021, 2022, 2023
Chu Kochen Presidential Scholarship, Zhejiang University, 2023
SenseTime Scholarship, 2022
Academic Services
Program Committee / Reviewer for AAAI, CVPR, ECCV, NeurIPS
Mentor at CMU Paths to AI Research (PAIR) Program, 2025
Member of CMU School of Computer Science Dean's Advisory Committee, 2025
Teaching Assistant for Computer Vision,
ZJU,
2023
Conference Volunteer for AAAI, 2024
Miscellaneous
I love recording and understanding how nature paints with light.
I also enjoy a wide range of sports and spent five lovely years on a professional badminton team.
Top
