Hyung Won Chung
Research scientist at OpenAI; previously a key author at Google on Flan-T5, PaLM, and instruction tuning.
- Role
- researcher
- Currently at
- OpenAI
- twitter.com/hwchung27
- Scholar
- scholar.google.com/citations
- Papers
- 10
Cite
Notes
Only stored in your browser.
Authored papers
10BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
preprint
GPT-4 Technical Report
gpt-4-technical-report
The Flan Collection: Designing Data and Methods for Effective Instruction Tuning
arXiv 2023
UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining
arXiv 2023
Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them
ACL
Scaling Up Models and Data with $\texttt{t5x}$ and $\texttt{seqio}$
arXiv 2022
What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?
arXiv 2022
Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers
arXiv 2021
Do Transformer Modifications Transfer Across Implementations and Applications?
EMNLP 2021 11
Learning Compact Metrics for MT
EMNLP 2021 11
Affiliations
Previously
Frequent co-authors
10from 10 papers
Adam Roberts
Yi Tay
founder
Jason Wei
research-scientist
Sharan Narang
Colin Raffel
William Fedus
founder
Aakanksha Chowdhery
researcher
Barret Zoph
founder
Denny Zhou
researcher
Noah Fiedel