影响力指数

2.77/100

超过 8%

全站排名 #59,203

发表论文4 篇

平均评分5.0

年均产出2.0 篇/年

Peiyang Xu

PhD student@Princeton University·美国·OpenReview

研究方向

Trustworthy Machine Learning · AI Safety · Mulltimodal Models

Mitigating Object Hallucination in Large Vision-Language Models through Adversarial Contrastive Finetuning

ICLR 2026Rejected

SAFEVISION: Efficient Image Guardrail with Robust Policy Adherence and Explainability

ICLR 2026Rejected

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

ICLR 2025Poster

SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability

ICLR 2025Rejected

合作者 (20)

Alexander Xiong