影响力指数

-/100

发表论文2 篇

平均评分4.0

年均产出2.0 篇/年

Yuxi Li

MS student@Huazhong University of Science and Technology·中国·OpenReview

Circumventing Safety Alignment in Large Language Models via Embedding Space Toxicity Attenuation

ICLR 2026Rejected

Evading Safety Alignment in Open-source LLM Deployment by Embedding Semantic Shift

ICLR 2026Rejected

合作者 (6)