👋 Hi! I am a senior undergraduate at Before, I
E-mail: tongyuxuan361@gmail.com / tongyx21@mails.tsinghua.edu.cn |
I aim to build AI systems to better serve every human being, especially for complex intellectual activities.
Specifically, I am interested in the following topics:
Large Language Model (LLM)
AI for (Advanced)
Education (e.g. Eureka Labs)
Research (e.g. SciCode-Bench)
Software Engineering (e.g. SWE-Bench)
Scalable Alignment(e.g. Scalable Oversight)
Hardware-Aware Algorithm Design (e.g. Flash Attention)
(*) denotes co-first authors
Yuxuan Tong, Xiwen Zhang, Rui Wang, Ruidong Wu, Junxian He
Accepted by NeurIPS 2024
[📝 Paper@arXiv]
[🧠 Publication@NeurIPS]
[🤗 Datasets&Models@HF]
[🐱 Code@GitHub]
[🐦 Thread@X(Twitter)]
[🐶 中文博客@知乎]
[📊 Leaderboard@PapersWithCode]
[📑 BibTeX]
Jiazheng Xu*, Xiao Liu*, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, Yuxiao Dong
Accepted by NeurIPS 2023
[📝 Paper@arXiv]
[🧠 Publication@NeurIPS]
[🖼️ Dataset@HF]
[🤖 Model@HF]
[🐦 Thread@X(Twitter)]
[🐶 中文博客@知乎]
[📑 BibTeX]
Undergraduate (2021.09 - present)
Department of Computer Science and Technology (DCST), Tsinghua University (THU)
Bachelor's degree in progress
GPA: 3.8/4.0
2024.07 - 2024.09
CX Group, Language Technologies Institute (LTI), Carnegie Mellon University (CMU)
Research intern, advised by Prof. Chenyan Xiong.
Worked on data for on-line (direct) preference optimization algorithms (e.g. DPO).
2023.07 - 2024.06
NLP Group, Hong Kong University of Science and Technology (HKUST-NLP)
Research intern, advised by Prof. Junxian He.
Worked on synthetic data for mathematical reasoning since 2023.12,
before which I worked on
process supervision and constrained decoding for mathematical reasnoning,
model merging.
2022.11 - 2023.06
Research intern, advised by advised by Prof. Jie Tang and Prof. Yuxiao Dong.
Worked on reward modeling and RLHF for text-to-image generation.
Data-Centric Method for Enhancing Mathematical Problem-Solving of LLMs (2023.12 - present)
Admitted as B-Level in Tsinghua University Initiative Scientific Research Program in 2024
End-to-End Evaluation Model for Text-to-Image Generation (2023.04 - 2023.11)
Admitted and completed as A-Level (top 25%) in Tsinghua University Initiative Scientific Research Program in 2023
Maintainer of the GitHub Repository THUDM/ImageReward
In addition to regular contribution and maintainment, I integrated our ImageReward into Stable Diffusion Web UI
Tsinghua University Research Scholarship (2024)
Tsinghua University Research Scholarship (2023)
Tsinghua University Comprehensive Merit Scholarship (top 5% undergraduates) (2022)
Conference Review: NeurIPS 2024, NeurIPS’24 Workshop on Math-AI, ICLR 2025
Programming Languages: Python, C/C++, TypeScript/JavaScript, etc.
ML Libraries: PyTorch, DeepSpeed, HuggingFace, vLLM/SGLang, etc.
Tools: Git, Shell, SLURM, Linux Utilities, LaTeX, etc.
I am from Shengzhou (嵊州), Shaoxing, Zhejiang in China, which is the birthplace of Yue Opera (越剧) and also famous for delicious food like Xiaolongbao (小笼包).
I spent six years (2009-2015) of my childhood at Yaohua Primary School (耀华小学) in Tianjin, which is quite happy time.
Before entering Tsinghua University, I studied at Shengzhou High School (嵊州中学), which is located in a small town but full of excellent teachers and classmates.