| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://taiweis.com/
x-github-request-id: 292C:234FE9:8DEE67:9F31FE:695274EA
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 12:32:43 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210068-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767011563.958101,VS0,VE247
vary: Accept-Encoding
x-fastly-request-id: b70a0a77fda4ea0bf668ebd786ab86f42f4408f3
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Fri, 26 Sep 2025 03:48:45 GMT
access-control-allow-origin: *
etag: W/"68d60d1d-36be"
expires: Mon, 29 Dec 2025 12:42:43 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: FA14:1387E:8BD83A:9D1BFB:695274EB
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 12:32:43 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210045-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767011563.343970,VS0,VE208
vary: Accept-Encoding
x-fastly-request-id: 13038edd7383421fda4e033729bbf6cde74a3a75
content-length: 3489
Taiwei Shi
Taiwei Shi is a Ph.D. student at University of Southern California, advised by Professor Jieyu Zhao. Previously, he graduated from the Georgia Institute of Technology with a Bachelor of Computer Science degree. He is from Dongguan, China.
At Georgia Tech, he was fortunate to be advised by Professors Mark Riedl and Diyi Yang. He spent some of his summers doing research at Microsoft Research and USC ISI.
His research interest mainly revolves around natural language processing and computational social science. Recently, he is particularly excited about reinforcement learning, synthetic data, and human-AI interaction.
Featured Research Publications
Latest research for fans of natural language processing.
Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
Preprint
2025
Enabling LLMs to Reason About Uncertainty
EMNLP Findings
2025
Aligning LLMs With In-situ User Interactions And Feedback
Preprint
2024
Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base
COLM
2025
Introducing computer-using agents with coding as actions, a novel paradigm for task automation.
Preprint
2025
Safer-Instruct Aligning Language Models with Automated Preference Data
NAACL
2024
