Back

About

views | comments

Yutong Liang

Yutong Liang

Guess what? Click the image to change it!

Hi there! 👋 I'm Yutong Liang, a 4th-year undergraduate student at the School of EECS , Peking University, majoring in Computer Science.

I have a vision of creating generalist agents that can do what we humans can do. I'm particularly interested in endowing them with human-level dexterity to master complex human-object interaction (HOI) and in-hand manipulation tasks.

I explored these interests in character animation as a research student in the VCL Lab at Peking University from Fall 2023 to Summer 2025, where I was advised by Prof. Libin Liu.

I served as a Teaching Assistant for the Introduction to AI course at Peking University in Spring 2025.

During summer 2024, I was a research intern at Stanford University, where I worked with Michelle Guo and Pei Xu in the TML Lab and SVL Lab, under the guidance of Prof. Karen Liu and Prof. Jiajun Wu.

Previously, I researched in the field of Data Structures in Network Measurement in Spring 2023, supervised by Prof. Tong Yang.

Publications

Please visit my publications page for more projects!

ROBOVERSE: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning
ROBOVERSE: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

Author List

Haoran Geng*, Feishi Wang*, Songlin Wei*, Yuyang Li*, Bangjun Wang*, Boshi An*, Charlie Tianyue Cheng*, Haozhe Lou, Peihao Li, Yen-Jen Wang, Yutong Liang, Dylan Goetting, Chaoyi Xu, Haozhe Chen, Yuxi Qian, Yiran Geng, Jiageng Mao, Weikang Wan, Mingtong Zhang, Jiangran Lyu, Siheng Zhao, Jiazhao Zhang, Jialiang Zhang, Chengyang Zhao, Haoran Lu, Yufei Ding, Ran Gong, Yuran Wang, Yuxuan Kuang, Ruihai Wu, Baoxiong Jia, Carlo Sferrazza, Hao Dong, Siyuan Huang, Koushil Sreenath, Yue Wang†, Jitendra Malik†, Pieter Abbeel†

Robotics: Science and Systems (RSS) , 2025

Technical Description

ROBOVERSE comprises a scalable simulation platform, a large-scale synthetic dataset, and unified benchmarks. The simulation platform supports seamless integration of new tasks and demonstrations through unified protocols, ensuring flexibility and extensibility. The dataset includes over 1,000 diverse tasks and more than 10 million transitions, constructed through large-scale data migration, cross-embodiment transfer, and robust augmentation and randomization.
SimiSketch: A Sketching Algorithm for Similarity Estimation
SimiSketch: A Sketching Algorithm for Similarity Estimation

Fenghao Dong, Yutong Liang*, Yang He*, Zirui Liu, Yuhan Wu, Peiqing Chen, and Tong Yang

arXiv preprint 2405.19711 , 2024

Technical Description

We propose SimiSketch, a sketching algorithm designed to tackle the specific problem of estimating similarity between sets. We first present two simpler versions that employ intuitive sketches for similarity estimation. Subsequently, we formally introduce SimiSketch and leverage SALSA to enhance accuracy. To validate our algorithms, we conduct extensive testing on synthetic datasets, real-world network traffic, and text articles. Our experiment shows that compared with the state-of-the-art, SimiSketch can improve the accuracy by up to 42 times, and increase the throughput by up to 360 times. The complete source code is open-sourced and available on GitHub for reference.

Education

Skills and Tools

Language
C
Programming Language
C++
Programming Language
Python
Programming Language
Rust (Learning)
Programming Language
Latex
Paper & Homework Writing
Typst
Paper & Homework Writing
Markdown
Docs & Blogs Writing
Shell
Scripting
Coding
Warp
Terminal
Cursor
IDE
VS Code
IDE
GitHub
Code Hosting
Git
Version Control
PyTorch
Deep Learning & Optimization
Development Tools
Rerun
Visualize multimodal data over time
Blender
3D Modeling
CVAT
Annotation Tool
Docker
Containerization
Productivity
Arc
Broswer
Safari
Broswer
Notion
Literature Review & Keep Diary
Typora
Markdown Editor
Environment
MacOS Sonoma
MacBook Pro
Ubuntu 22.04 LTS
Linux Distribution

Personal Interests

  • I am passionate about Speed Cubing (solving Rubik's Cubes as quickly as possible) and currently hold the Peking University record for Pyraminx Single (valid through June 2025)!

    My personal bests include a 9.47-second solve for the 3x3 cube at Los Angeles 2024 and a 2.36-second Pyraminx solve at Sacramento 2024. You can find more details on my WCA profile.

    Curious about speed-cubing? Check out this YouTube video! I also share Rubik's Cube blogs on this site—feel free to explore them!

  • I also enjoy playing tennis! While I'm not a professional, I play for the fun and excitement of the game.

What TV show do you like?

I love watching Doctor Who! It gives me a sense if seeing the world in a different way.I've been watching it for 10 years now, from Peter Capaldi and I'm still not tired of it. Here're some blogs about it!

What anime do you like to watch?

I have watched these anime! I fell in love with the music in Your Lie in April the first time I listened to them!

What is your favorite book?

I love reading the Harry Potter series. I've read it many times before watching Doctor Who.
Comment seems to stuck. Try to refresh?✨