About

Zhefei Gong

Hi, I’m an incoming PhD student at Khoury College of Computer Science at Northeastern University, advised by Prof. Robert Platt. Previously, I have worked with Prof. Jiachen Li and Prof. Donglin Wang. I earned my BEng in Computer Science from Tongji University, including a memorable semester as an exchange student at EPFL. During my time at Tongji, I also had the opportunity to engage with the IRCP Lab and gain early research experience.

After an extensive period of exploration, my interest has gravitated towards solving real-world tasks. I am currently interested in robot learning, generative models and reinforcement learning, particularly for manipulation tasks. My long-term goal is to enable general-purpose robots to learn autonomously in dynamic, unstructured environments, bridging the gap from lab demonstrations to everyday human settings. I aspire to develop robots capable of performing complex, long-term daily tasks independently, and I am dedicated to advancing this vision over the next decade. Feel free to get in touch if our research interests align.

News

[Jan.31st, 2026] Happy to share that my first-author paper, KORR, has been accepted to ICRA 2026! Many thanks to my co-authors.
[Jun.25th, 2025] Thrilled to share that my first first-author paper, CARP, has been accepted to ICCV 2025! Huge thanks to everyone who supported me along the way.
[Jun.24th, 2025] Joined TASL as a visiting scholar and Excited for the journey ahead!
[Jan.23rd, 2025] One paper on vision-language-action model (VLAS) has been accepted to ICLR 2025!
[Jul.9th, 2024] Joined MiLab as a research assistant working on Robot Learning. Wish me luck!
[Jul.1st, 2024] Graduated from Tongji University with four years of wonderful memories, and here's my undergrad thesis.

Research

Care-Moma
Causal Residual Learning for Mobile Manipulation via Efficient Human-in-the-Loop Fine-Tuning Zhefei Gong, Jiachen Li Preprint, 2026 Links: video | TBD
KORR
Robust Online Residual Refinement via Koopman-Guided Dynamics Modeling Zhefei Gong, Shangke Lyu, Pengxiang Ding, Wei Xiao, Donglin Wang IEEE International Conference on Robotics and Automation (ICRA), 2026 Links: arXiv | website | code
CARP
CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction Zhefei Gong, Pengxiang Ding, Shangke Lyu, Siteng Huang, Minyang Sun, Wei Zhao, Zhaoxin Fan, Donglin Wang International Conference on Computer Vision (ICCV), 2025 Links: arXiv | website | code
VLAS
VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation Wei Zhao, Pengxiang Ding, Zhang Min, Zhefei Gong, Shuanghao Bai, Han Zhao, Donglin Wang The Thirteenth International Conference on Learning Representations (ICLR), 2025 Links: arXiv | code

Projects

Manipulation-Consistency
On the Synergy of Structured Visual Representation Learning and Embodied Self-Supervised Learning Zhefei Gong, Alexandre Alahi Semester Project at EPFL Links: Report | Thesis(zh)
Vehicle-ReIdentification
Intelligent Park Unmanned Parking Method Based on Space-Time Vehicle Re-Identification Worked with professors and graduate students Completed during internship at IRCP Lab Links: Patent | Patent(zh)

Awards