Skip to main content

Hit enter to search or ESC to close

About
Use Case
Publications
Research
- Research
- Github
- Huggingface
- Blog
Culture

KR

Is the Importance Ratio Necessary for Stable Reinforcement Learning in LLMs?

Shuibai Zhang*, Junhyuck Kim*, Gyeongman Kim, Jaewoong Cho

Abstract

Language Model

NeurIPS 2026

Download Paper

Github Code

Share Share Share Pin

KRAFTON, Inc.

Address: Centerfield EAST, 231, Teheran-ro, Gangnam-gu, Seoul, 06142, Republic of Korea

Privacy Policy

Copyright @ 2023 KRAFTON. All rights reserved

About
Use Case
Publications
Research
- Research
- Github
- Huggingface
- Blog
Culture
KR