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

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).

Continuous 3D Perception Model with Persistent State

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.

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

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.

FastMAC: Stochastic Spectral Sampling of Correspondence Graph

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.

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

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.

AIR Industrial Showroom Setup

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.

iFLYTEK 10.24 Industrial Big Model Launch Event

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

Autonomous Driving Mini-car

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

Selected Honors and Awards

Designed based on Jon Barron's website