Tianyi Zhang (original) (raw)
Final-year Ph.D. student @ Stanford AI
I want to work on SWE agents!
POSTS
Scaling RL Environments for SWE Agents
TL;DR: I think we are near executing a ton of repos and do RL on them.
PAPERS
Alpaca: An Open Instruction-Following Model
Rohan Taori*, Ishaan Gulrajani*, Tianyi Zhang*, Yann Dubois*, Xuechen Li*, Carlos Guestrin, Percy Liang, Tatsunori B. Hashimoto
blogpost code
AlpacaFarm: A Simulation Framework for RLHF
Yann Dubois*, Xuechen Li*, Rohan Taori*, Tianyi Zhang*, Ishaan Gulrajani, Jimmy Ba, Carlos Guestrin, Percy Liang, Tatsunori B. Hashimoto
paper blogpost code
BERTScore: Evaluating Text Generation with BERT
ICLR 2020
Tianyi Zhang*, Varsha Kishore*, Felix Wu*, Kilian Q. Weinberger, Yoav Artzi
paper code
Simplifying Graph Convolutional Networks
ICML 2019
Felix Wu*, Tianyi Zhang*, Amauri Holanda de Souza Jr*., Christopher Fifty, Tao Yu, Kilian Q. Weinberger
paper code poster
WORK AND SERVICE
- Meta AI Research. Research Intern. 2022.6 - 2022.9
- ASAPP Inc. Research Intern. 2019.3 - 2020.7
- Reviewer: NeurIPS (2020 - 2022), ICLR (2021 - 2022, 2021 Outstanding Reviewer Award), TMLR, TPAMI
- NeurIPS 2019 Student Volunteer