1 citations · 3 across the 9 of their papers we have counts for
9 papers
Assessing Adversarial Robustness of Latent Reasoning Models
Shaolong Chen, Ang Li, Mingjie Li +1
Large language models increasingly rely on long chain-of-thought (CoT) trajectories for complex reasoning, but autoregressive generation brings substantial memory and inference cos…
TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models
Yichuan Mo, Yukun Jiang, Yanbo Shi +4
The rapid development of Language Diffusion Models (LDMs) challenges the dominant position of auto-regressive competitors in language processing. However, their flexible, any-order…
Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms
Mingjie Li, Wai Man Si, Michael Backes +2
Despite the impressive performance of general-purpose large language models (LLMs), they often require fine-tuning or post-training to excel at specific tasks. For instance, large…
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…
Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning
Ang Li, Yichuan Mo, Mingjie Li +2
Large Language Models (LLMs) have demonstrated remarkable success across various NLP benchmarks. However, excelling in complex tasks that require nuanced reasoning and precise deci…
MADE: Graph Backdoor Defense with Masked Unlearning
Xiao Lin, Mingjie Li, Yisen Wang
Graph Neural Networks (GNNs) have garnered significant attention from researchers due to their outstanding performance in handling graph-related tasks, such as social network analy…
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…
TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
Yichuan Mo, Hui Huang, Mingjie Li +2
Diffusion models have achieved notable success in image generation, but they remain highly vulnerable to backdoor attacks, which compromise their integrity by producing specific un…
PID: Prompt-Independent Data Protection Against Latent Diffusion Models
Ang Li, Yichuan Mo, Mingjie Li +1
The few-shot fine-tuning of Latent Diffusion Models (LDMs) has enabled them to grasp new concepts from a limited number of images. However, given the vast amount of personal images…