5 papers
AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective
Zhenyi Wang, Siyu Luan
As machine learning (ML) systems expand in both scale and functionality, the security landscape has become increasingly complex, with a proliferation of attacks and defenses. Howev…
CORE: Context-Robust Remasking for Diffusion Language Models
Kevin Zhai, Sabbir Mollah, Zhenyi Wang +1
Standard decoding in Masked Diffusion Models (MDMs) is hindered by context rigidity: tokens are retained based on transient high confidence, often ignoring that early predictions l…
Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation
Chongcong Jiang, Tianxingjian Ding, Chuhan Song +7
Promptable segmentation foundation models such as SAM3 have demonstrated strong generalization capabilities through interactive and concept-based prompting. However, their direct a…
Dynamic Feedback Engines: Layer-Wise Control for Self-Regulating Continual Learning
Hengyi Wu, Zhenyi Wang, Heng Huang
Continual learning aims to acquire new tasks while preserving performance on previously learned ones, but most methods struggle with catastrophic forgetting. Existing approaches ty…
Understanding Catastrophic Interference: On the Identifibility of Latent Representations
Yuke Li, Yujia Zheng, Tianyi Xiong +2
Catastrophic interference, also known as catastrophic forgetting, is a fundamental challenge in machine learning, where a trained learning model progressively loses performance on…