Yifei Zhang | 张逸飞

I am an undergraduate student studying Artificial Intelligence at University of Chinese Academy of Sciences (UCAS). I am currently a visiting research scholar at BAIR, UC Berkeley, working with Dr. Qianqian Wang under the guidance of Prof. Angjoo Kanazawa and Prof. Alexei (Alyosha) Efros. I also work closely with Prof. Masayoshi Tomizuka. My previous experience includes an internship at Institute for AI Industry Research (AIR), Tsinghua University, where I was advised by Prof. Hao Zhao.

Email  /  CV  /  Scholar  /  Github

profile photo

Research

My research interest is 3D/4D Computer Vision and its application in Robotics. Specifically, I would love to explore building representations of the dynamic 3D world from everyday videos, streaming sensory inputs from multiple modalities, and interactions with the environment. Ultimately, my goal is to create intelligent agents with human-like perception abilities. Selected works are listed below (*equal contribution).

project image

Continuous 3D Perception Model with Persistent State


Qianqian Wang*, Yifei Zhang*, Aleksander Holynski, Alexei A Efros, and Angjoo Kanazawa
CVPR 2025
arxiv / code / website /

A new framework for reasoning about the 3D world in an online, sequential manner. Given an input image stream, our method simultaneously updates an inner state with the current observation and reads from it to make predictions of 3D geometry & camera pose for the current view, as well as infer unseen portions of the scene.

project image

Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning


Yixiao Wang*, Yifei Zhang*, Mingxiao Huo*, Ran Tian, Xiang Zhang, Yichen Xie, Chenfeng Xu, Pengliang Ji, Wei Zhan, Mingyu Ding, and Masayoshi Tomizuka
CoRL 2024
arxiv / code / website /

We propose a Sparse Diffusion Policy (SDP) that integrates a Mixture of Experts module specifically designed for multitask learning, continual learning and rapid adaptation to new tasks.

project image

FastMAC: Stochastic Spectral Sampling of Correspondence Graph


Yifei Zhang, Hao Zhao, Hongyang Li, and Siheng Chen
CVPR 2024
arxiv / code /

We propose a new technique of stochastic spectral sampling of correspondence graph and build a complete 3D registration pipeline that reaches real-time speed while leading to little to none performance drop.

project image

Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Loss


Yifei Zhang, Huan-ang Gao, Zhou Jiang, and Hao Zhao
NeurIPS 2024
arxiv / code /

A new fluid motion tracking method that is completely self-supervised and notably outperforms its supervised counterparts while requiring only 1% of the training samples (without labels) used by previous methods.

Industrial Projects

A sampling of projects on robotics during my internship at AIR, Tsinghua University.

project image

AIR Industrial Showroom Setup


industry
2023-12-01

In charge of display systems for Tsinghua University’s showroom, enabling remote control of autonomous vehicles, resulting in improvement in system efficiency through advanced Unity and ROS communications.

project image

iFLYTEK 10.24 Industrial Big Model Launch Event


industry
2023-10-24

Led debugging and optimization of robotic arm hardware drivers for the iFLYTEK 10.24 launch, contributing to a successful product demonstration.

project image

Autonomous Driving Mini-car


industry
2023-08-01

Constructed an autonomous robot capable of complex environment navigation. Led the development and implementation of sophisticated mapping and navigation algorithms.

Selected Honors and Awards

  • 2024: SenseTime Scholarship (Only 25 winners nationwide)
  • 2023-2024: China National Scholarship (Top 0.01%, Highest Honor for undergraduates in China)
  • 2022-2024: First-Level Scholarship of UCAS (Top 1% in UCAS)
  • 2023: Honorable Mention in Mathematical Contest in Modeling (Top 10% around the world)
  • 2023: 3V3 National Second Prize in RoboMaster University League
  • 2023: National First Prize in APMCM (Top 5% in China)

Designed based on Jon Barron's website