Tianyang Liu
Ph.D. Student at UC San Diego
I am a Ph.D. student (2024-) in Computer Science at UC San Diego, advised by Prof. Julian McAuley.
My research focuses on Natural Language Processing (NLP), and I am broadly interested in Large Language Models (LLMs). Specifically, I explore areas such as reasoning (LLM Reasoners), tool augmentation (ToolkenGPT), and code generation (RepoBench, StarCoder2). I am also interested in building code agents. Currently, I am deeply engaged in LLM evaluation, believing that the future belongs to those who do evals. \(^†\)
Prior to my Ph.D. studies, I completed my Master’s degree in Computer Science at UC San Diego, working with Prof. Julian McAuley and Prof. Zhiting Hu. During this time, I also collaborated with Prof. Muhao Chen from UC Davis. Before that, I earned my Bachelor’s degree from Wuhan University. I have also interned at NVIDIA, working with Gaoyan Xie and his team on CUDA code agents.
I am actively seeking undergraduate and master’s students interested in collaborating on research projects related to code generation, agents, benchmarking, reasoning, and similar topics. If you’re passionate about these areas, please don’t hesitate to email me.
News
Oct 10, 2024 | 🤖 We pre-release Decentralized Arena for automated, scalable, and transparent LLM evaluation. |
---|---|
Sep 20, 2024 | 🎉 DRPO is accepted to the main conference of EMNLP 2024! |
Jul 10, 2024 | 🎉 LLM Reasoners is accepted to COLM 2024! |
Feb 28, 2024 | 💫 We release StarCoder 2, a family of open LLMs for code. |
Jan 16, 2024 | 🎉 RepoBench gets accepted to ICLR 2024! |
Selected Publications [view all]
2024
- pre-releasePre-release, 2024Final version will be released soon.
- EMNLP (main)
- COLMCOLM, 2024Also to appear at Large Language Model (LLM) Agents workshop at ICLR 2024
- NAACL
2023
Services
Invited Reviewer
- AAAI
- ICLR
- AISTATS
- NeurIPS
- COLM
- ICML
- ICLR
- ACL ARR (Feb, Apr, Jun, Aug, Oct)
- ACL ARR (Dec)
- NLPCC