👋 I am currently pursuing a MPhil degree in data science at Tsinghua University, with a research focus on 3D AIGC.
🤔 My research interests include large language models, large multimodal models, image, video, and 3D generative model. I very much enjoy LLM-related research because I think it is the best way to achieve AGI at this point in time. However, the main research work I will be doing in the next few years will be focused on 3D vision.
🤖 I am currently working on research related to LLM as Agent, 2D/3D AIGC, and 3D Avatar, especially in areas that have a strong connection to humans. And would like to realize AGI for the benefit of humanity through generative AI.
🙋♂️ If you are seeking any form of academic cooperation, please feel free to email me at yisuanwang AT gmail DOT com.
⬅️ What is AIGC? Move your mouse over the avatar on the left to see it! 🤯
🎓 I graduated from Harbin Engineering University with a B.S. degree in Software Engineering, supervised by Prof. Chao Li. I had an internship at the Institute of Automation, Chinese Academy of Sciences, supervised by Prof. Yubo Chen. In addition, I had a good time with Prof. Hao Zhao at Institute for AI Industry Research (AIR), Tsinghua University.
😥 I’ll be emo on a regular basis, which looks to be caused by not being able to write a paper.
🔥 News
- 2024.03: 🎉 We released Ultraman, which converts a single image of the human body into a lifelike 3D model!
- 2024.03: 🎉 We released Idea-2-3D, which enables automated 3D model design and generation for people!
- 2024.02: 🎉 One paper is accepted by COLING 2024! Congratulations to Dr. Ye!
- 2023.12: 🎉 We released Soulstyler, which enables fine-grained stylization of a single image through text-guidance!
📝 Publications
🧑🎨 3D AIGC
Idea-2-3D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs
Junhao Chen *, Xiang Li *, Xiaojun Ye, Chao Li, Zhaoxin Fan, Hao Zhao †
[🗂️Project Page] |
- This work enables automated 3D model design and generation for people!
Ultraman: Single Image 3D Human Reconstruction with Ultra Speed and Detail
Mingjin Chen *, Junhao Chen *, Xiaojun Ye, Huan-ang Gao, Xiaoxue Chen, Zhaoxin Fan, Hao Zhao †
- This work converts a single image of the human body into a lifelike 3D model!
👀 MM & LMM
MMAD:Multi-modal Movie Audio Description
Xiaojun Ye, Junhao Chen, Xiang Li, Haidong Xin, Chao Li, Sheng Zhou †, Jiajun Bu
- This work has unlocked a whole new experience of watching movies for the visually impaired.
Soulstyler: Using Large Language Model to Guide Image Style Transfer for Target Object
Junhao Chen, Peng Rong, Jingbo Sun, Chao Li †, Xiang Li, Hongwu Lv
- This work enables fine-grained stylization of a single image through text-guidance!
🎙 NLP & LLM
Towards Energy-Efficient Sentiment Classification with Spiking Neural Networks
Junhao Chen, Xiaojun Ye, Jingbo Sun, Chao Li †
- This work applies a pulsed neural network to a natural language sentiment categorization task, reaching the leading edge in terms of energy consumption.
ZhuJiu: A Multi-dimensional, Multi-faceted Chinese Benchmark for Large Language Models
Baoli Zhang *, Haining Xie *, Pengfan Du, Junhao Chen, Pengfei Cao, Yubo Chen †, Shengping Liu, Kang Liu, Jun Zhao
[🗂️Project Page] [🏆Leaderboard ] [📜Paper] [🎥Video]
- This work serves as a benchmark for evaluating the Chinese language capabilities of large language models.
📃Patents
Id | Date | Name | Number | Type |
---|---|---|---|---|
6 | 2024-03-22 | 一种盲人智能眼镜 | - | China Utility Model |
5 | 2024-03-22 | 一种拼接摄像头 | CN220647706U | China Utility Model |
4 | 2023-06-21 | 一种基于神经网络的本地化经验威胁分析方法及装置 | CN116962012A | China Invention Publication |
3 | 2023-06-21 | 一种基于面向流切分技术的网络日志解析方法及装置 | CN116668154A | China Invention Publication |
2 | 2022-10-31 | 一种数控机床的废料回装置 | CN218312317U | China Utility Model |
1 | 2021-12-27 | 一种舰船用高分辨率超远距全景摄像头 | CN216565344U | China Utility Model |
📄Software copyrights
Id | Date | Name | Number |
---|---|---|---|
7 | 2023-10-25 | Tallybook:一款记账管理系统 | 2023SR1295186 |
6 | 2023-08-04 | 基于深度学习的鸟类声音识别系统 | 2023SR0896658 |
5 | 2023-08-02 | 法保——专注小微企业的法律咨询平台 | 2023SR0881467 |
4 | 2023-05-18 | 灵魂画手——数字照片资产修复与管理软件iOS App | 2023SR0551686 |
3 | 2023-05-18 | Soul Painter基于深度学习图像处理技术的Android App | 2023SR0551505 |
2 | 2022-05-26 | 计算机视觉目标定位测距系统 | 2022SR0649919 |
1 | 2022-05-26 | 基于深度学习的物体识别处理系统 | 2022SR0649918 |
🎖 Honors and Awards
Innovation and Entrepreneurship Competition Award Cumulative Awards National *9, Provincial *39, School-level *11, totaling 59.
Honors awards cumulative awards national *6, provincial *1, school-level *18, a total of 25.
Competition awards and individual honors total 84 (as of March 22, 2024).
Selected Awards and Honors
📖 Educations
- 2024.09 - 2027.06, Master, Shenzhen International Graduate School (SIGS), Tsinghua University, Shenzhen.
- 2021.09 - 2024.06, Undergraduate, College of Software, Harbin Engineering University, Harbin.
- 2020.09 - 2021.06, Undergraduate, College of Electromechanical Engineering, Harbin Engineering University, Harbin.
- 2017.09 - 2020.06, Nanfang High School, Zhuzhou.
💬 Invited Talks
- 2024.01, 百度高校合作: 终于找到“老照片”的正确打开方式了!
- 2023.09, 哈尔滨工程大学校友会:【工程学子第25期】投身科研,热爱实践
- 2023.06, 哈尔滨工程大学团委: 阳光论坛|“我的成长故事汇”校庆系列活动计算机科学与技术学院专场报告会
- 2023.06, 哈尔滨工程大学团委:【阳光回顾】科技探索,计算创新,成长故事谱写青春靓丽篇章
- 2023.05, 哈尔滨工程大学团委:校庆·我的成长故事汇|投身科研,热爱实践,看计科学子发光发热,奔赴山海
💻 Internships
- 2023.09 - 2024.03, Institute for AI Industry Research (AIR), Tsinghua University, Beijing.
- 2023.04 - 2023.09, Institute of Automation, Chinese Academy of Sciences, Beijing.
- 2021.07 - 2023.04, Modeling and Emulation in E-Government National Engineering Laboratory, Harbin.