影响力指数

-/100

发表论文2 篇

平均评分3.8

年均产出1.0 篇/年

Junchi Liao

MS student@University of Electronic Science and Technology of China·中国·OpenReview

研究方向

LLM · AI Safety · Reinforce Learning

Backdooring CLIP through Concept Confusion

ICLR 2026Withdrawn

Representation Confusion: Towards Representation Backdoor on CLIP via Concept Activation

ICLR 2025Rejected

合作者 (9)