影响力指数

35.72/100

前 18.1%

全站排名 #11,674

发表论文7 篇

平均评分5.8

年均产出2.3 篇/年

Geon-Hyeong Kim

Researcher@LG AI Research·韩国·OpenReview

研究方向

Imitation Learning · Reinforcement Learning · Variational Inference

SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety

Designing Observation and Action Models for Efficient Reinforcement Learning with LLMs

ICLR 2026Rejected

Online Pre-Training for Offline-to-Online Reinforcement Learning

ICML 2025Poster

SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety

ICLR 2025Rejected

Online Pre-Training for Offline-to-Online Reinforcement Learning

ICLR 2025Rejected

合作者 (18)