Han Shen

~Han_Shen3

2

论文总数

2.0

年均投稿

5.7

平均评分

接收情况1/2

会议分布

ICLR

2

发表论文 (2 篇)

20252 篇

SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection

ICLR 2025Poster

Mitigating Forgetting in LLM Supervised Fine-Tuning and Preference Learning

ICLR 2025Rejected

合作者 (8)

Tianyi Chen2 篇

Pin-Yu Chen1 篇

Heshan Devaka Fernando1 篇

Horst Samulowitz1 篇

Nathalie Baracaldo1 篇

Parikshit Ram1 篇