1 citations · 4 across the 13 of their papers we have counts for
4 papers · 1 filter
Decoding Large Language Diffusion Models with Foreseeing Movement
Yichuan Mo, Quan Chen, Mingjie Li +2
Large Language Diffusion Models (LLDMs) benefit from a flexible decoding mechanism that enables parallelized inference and controllable generations over autoregressive models. Yet…
SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation
Mingjie Li, Wai Man Si, Michael Backes +2
As advancements in large language models (LLMs) continue and the demand for personalized models increases, parameter-efficient fine-tuning (PEFT) methods (e.g., LoRA) will become e…
On the Adversarial Transferability of Generalized "Skip Connections"
Yisen Wang, Yichuan Mo, Dongxian Wu +3
Skip connection is an essential ingredient for modern deep models to be deeper and more powerful. Despite their huge success in normal scenarios (state-of-the-art classification pe…
Adversarial Examples Are Not Real Features
Ang Li, Yifei Wang, Yiwen Guo +1
The existence of adversarial examples has been a mystery for years and attracted much interest. A well-known theory by \citet{ilyas2019adversarial} explains adversarial vulnerabili…