Hugging Face's logo
Activity Feed

AI & ML interests

Multi-modality Model, Data-centric AI

Recent Activity

THUOTAKUĀ  updated a dataset about 7 hours ago
CSU-JPG/IESBench
AwinyĀ  published a dataset about 8 hours ago
CSU-JPG/IESBench
AwinyĀ  submitted a paper about 9 hours ago
When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models
View all activity

Papers

When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models

VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation

View all Papers

CSU-JPG 's datasets 7