3 papers
cs.LG2026
Repurposing Adversarial Perturbations for Continual Learning: From Defense to Active Alignment
Ran Liu, Min Yu, Mingqi Liu +7
In dynamic environments, large language models need to keep adapting to new tasks, but continual learning often suffers from forgetting, limited transfer, and vulnerability to adve…
cs.CV2025
SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection
Yachao Liang, Min Yu, Gang Li +6
Detection of face forgery videos remains a formidable challenge in the field of digital forensics, especially the generalization to unseen datasets and common perturbations. In thi…
cs.CL2024
GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization
Ran Liu, Ming Liu, Min Yu +6
Pre-trained language models are increasingly being used in multi-document summarization tasks. However, these models need large-scale corpora for pre-training and are domain-depend…