6 citations · 6 across the 17 of their papers we have counts for
24 papers
Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape Analysis
Thong Bach, Dung Nguyen, Thao Minh Le +1
Existing attacks and defenses for diffusion-based large language models (dLLMs) target specific vulnerabilities but lack a shared framework explaining why attacks succeed. We propo…
EmoLASP: Emotion Recognition with Language Models and Answer Set Programming
Thao Le, Michael Thielscher
Emotion recognition in conversations is increasingly tackled with language models, but these models can be unstable and expensive to fine-tune or to prompt with long dialogue histo…
ASV3D: Adapting Diffusion-Based Single-View 3D Reconstruction with Extra Imagery
Y Huynh, Duc Thanh Nguyen, Thao Minh Le +1
Reconstruction of 3D objects from a single image is a fundamental research topic in computer vision. The key challenge is the lack of information from critical viewpoints to comple…
Continual Safety Alignment via Gradient-Based Sample Selection
Thong Bach, Dung Nguyen, Thao Minh Le +1
Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compromises safety behaviors, inc…
Curvature-Aware Safety Restoration In LLMs Fine-Tuning
Thong Bach, Thanh Nguyen-Tang, Dung Nguyen +2
Fine-tuning Large Language Models (LLMs) for downstream tasks often compromises safety alignment, even when using parameter-efficient methods like LoRA. In this work, we uncover a…
Rethinking Deep Alignment Through The Lens Of Incomplete Learning
Thong Bach, Dung Nguyen, Thao Minh Le +1
Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis revealing that position-depend…