Ryan Koo's picture

3 5

Ryan Koo

rngusry

·

https://kooryan.netlify.app

kooryan

AI & ML interests

NLP, RLHF, Alignment

Recent Activity

authored a paper about 1 month ago

Decoding the End-to-end Writing Trajectory in Scholarly Manuscripts

authored a paper about 1 month ago

Learning Explainable Dense Reward Shapes via Bayesian Optimization

upvoted a paper about 1 month ago

LawFlow : Collecting and Simulating Lawyers' Thought Processes

View all activity

Organizations

Papers 5

arxiv:2504.16272

arxiv:2401.14698

arxiv:2309.17012

arxiv:2305.09857

models 4

rngusry/llama-3.2-3b-ultrafeedback-rm

rngusry/llama-3.1-1b-ultrafeedback-rm

rngusry/llama3.2-1b-instruct-hh-sft

Text Generation • Updated Jan 22 • 9

rngusry/qwen2.5-hh-rm

Updated Jan 21 • 22

datasets 3

rngusry/UltraFeedback-honesty-preferences

Viewer • Updated Aug 3, 2024 • 251k • 34 • 1

rngusry/UltraFeedback-instruction_following-preferences

Viewer • Updated Jul 25, 2024 • 297k • 61

rngusry/UltraFeedback-truthfulness-preferences

Viewer • Updated Jul 25, 2024 • 217k • 49 • 1