影响力指数

20.22/100

前 41%

全站排名 #26,412

发表论文3 篇

平均评分4.8

年均产出1.5 篇/年

Jinqi Luo

Intern@Amazon·美国·OpenReview

研究方向

Multimodal Learning · Generative Models · Trustworthy Machine Learning

SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations

NeurIPS 2025Poster

KDA: A Knowledge-Distilled Attacker for Scalable LLM Red Teaming

ICLR 2025Withdrawn

PaCE: Parsimonious Concept Engineering for Large Language Models

NeurIPS 2024Poster

合作者 (8)

Kwan Ho Ryan Chan

Aditya Chattopadhyay

Chris Callison-Burch