Paper-Conference

On the Trustworthiness of Generative Foundation Models
Generative Foundation Models (GenFMs) have emerged as transformative tools. However, their widespread adoption raises critical concerns …
PDF Cite Project
On the Trustworthiness of Generative Foundation Models
Stealthy Backdoor Attack in Self-supervised Vision Encoders for Large Vision Language Models
Self-supervised learning (SSL) vision encoders learn high-quality image representations and thus have become a vital part of developing …
Zhaoyi Liu, Huan Zhang
PDF Cite Code
Stealthy Backdoor Attack in Self-supervised Vision Encoders for Large Vision Language Models
Interleaved Scene Graph for Interleaved Text-and-Image Generation Assessment
Unified Transformer-based models have enabled simultaneous multimodal understanding and generation, showing promise in unifying both …
Dongping Chen, Ruoxi Chen, Shu Pu, Zhaoyi Liu, Yanru Wu, Caixi Chen, Benlin Liu, Yue Huang, Yao Wan, Pan Zhou, Ranjay Krishna
PDF Cite Project
Interleaved Scene Graph for Interleaved Text-and-Image Generation Assessment
BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
Pixel-wise regression tasks (e.g., monocular depth estimation (MDE) and optical flow estimation (OFE)) have been widely involved in our …
Zhiyuan Cheng, Zhaoyi Liu, Tengda Guo, Shiwei Feng, Dongfang Liu, Mingjie Tang, Xiangyu Zhang
PDF Cite Code
BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks