Michael (Chengbo) Yuan   |   袁承博

🦊🦁🐮🐹🐰🐸🐶🐻🐨🐯

I am a Master student in Institute for Interdisciplinary Information Science (IIIS) at Tsinghua University, advised by Prof. Yang Gao🥳. Currently, my research interests mainly focus on Embodied AI (finding a way to achieve scalable robot learning), with the assistance of 3D computer vision (3DV).

Perviously, I have interned at MoonshotAI and MindSpore of Huawei. I am also interested in creating AI products or startups. I received my bachelor degree from the HongYi Honor class at the School of CS, Wuhan University😘, under the supervision of Prof. Yong Luo. I am also minoring in Law at School of Law and have a broad and extensive interest in philosophy and finance.

I welcome exploration, creation and excitement! 🤗🤩🤪

Google Scholar /  Github /  X(Twitter) /  WeBlog /  Zhihu

profile photo
contact me: ycb24@mails.tsinghua.edu.cn michaelyuancb@163.com
Recent
We release RoboEngine, the first plug-and-play and generalizable robot segmentation and augmentation models !
A pathway I envision for scalable robot intelligence, which forms the central theme of my research.
Check out General Flow as a possible representation for scalable robot learning !
Research

My research interests primarily focus on Embodied AI and 3D Computer Vision, particularly in utilizing vision-based methods to develop intelligent robotic systems with scalable ways. My ultimate aspiration is to create general-propose robots😎 that can truly understand and interact with our physical world.
(representative papers are highlighted)

RoboEngine: Plug-and-Play Robot Data Augmentation with Semantic Robot Segmentation and Background Generation
Chengbo Yuan*, Suraj Joshi*, Shaoting Zhu*, Hang Su, Hang Zhao, Yang Gao
project page / arXiv / code / dataset
In Submission, 2025

RoboEngine is the first plug-and-play visual robot data augmentation toolkit. Users can effortlessly generate physics-aware robot scenes with few lines code. This enable training only in one scenes and visual generalizing to almost arbitrary scenes.

Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos
Chengbo Yuan, Geng Chen, Li Yi, Yang Gao
project page / arXiv / code / thread
In Submission, 2025

We train EgoMono4D, a fast, dense and generalizable 4D reconstruction model for egocentric videos with label-free self-supervised methods. The training is conducted sole on unlabeled videos, potentially to apply to more label-scarce fields in the future.

General Flow as Foundation Affordance for Scalable Manipulation Learning
Chengbo Yuan, Chuan Wen, Tong Zhang, Yang Gao
project page / arXiv / code / openreview / thread
Conference on Robot Learning (CoRL), 2024

We build a 3D flow prediction model directly from large-scale RGBD human video datasets. Based on this model, we achieve stable zero-shot human-to-robot skill transfer in the real world.

Depression Diagnosis and Analysis via Multimodal Multi-order Factor Fusion
Chengbo Yuan, Yongqian Li, Qiancheng Yang, Qianhui Xu, Yong Luo
arXiv
International Conference on Artificial Neural Networks (ICANN), 2024

A multi-order factor fusion framework is designed to fuse text, audio, and video information for depression diagnosis.

MFT: Multi-scale Fusion Transformer for Infrared and Visible Image Fusion
Chen-Ming Zhang, Chengbo Yuan, Yong Luo, Xin Zhou
Paper
International Conference on Artificial Neural Networks (ICANN), 2023

A pyramid network architecture for infrared and visible image fusion.


Project
MindQuantFinance: High-Performance Quantitative Asset Pricing Library
A library for asset pricing (Q-quant) based on MindSpore
gitee
This is an AI+Finance project I participated in, where we built a high-performance library for derivative pricing based on MindSpore. It offers features such as Black-Scholes calculations, Monte Carlo simulations, and solutions to Backward SDE.
QFR: Tabular Prediction for Quantative Finance Research
A tabular prediction library designed for financial stock prediction.
github
This is one of the outcomes of an interesting experience, during which I worked with Prof. Jian Li on stock prediction problems. It provide rich tools for factors extraction and results prediction.
TaoClass: an AI-Driven Course Forum
A course forum powered by Large Language Models (LLMs) and Vector Databases (VD).
gitee
This is a project I led, and it also serves as the final assignment for the Software Engineering course at Wuhan University. The forum utilizes AI technology to offer natural language course selection and intelligent back-end information management.


Selected Awards and Honors

  • 2023: Lei Jun Outstanding Scholarship of Wuhan University (Highest-level Scholarship, 10/60k+, ¥100k RMB)
  • 2023: Outstanding Camper of the Recruitment Camp of Tsinghua PBC School of Finance
  • 2022: National Scholarship of Chinese Government (8000 RMB)
  • 2019: National Olympiad in Informatics (NOI2019), Silver Award (Class D)


  • Gallery



    This template is a modification to Yiran Geng's and Jon Barron's website.