collaborators

11 papers

cs.CV2026

Innocent Panels, Hateful Stories: Evaluating and Detecting Hateful Intent in Multi-Turn Visual Story Generation

Ye Leng, Junjie Chu, Yiting Qu +3

Picture books and comics have long been used to disseminate hateful narratives because they are easily understood even by children, as exemplified by the notorious Nazi propaganda…

cs.CL2026

Not All Tokens Matter Equally: Dynamic In-context Vector Distillation with Decisive-Token Supervision for Long-form Medical Report Generation

Ning Wu, Rui Liu, Xinkun Lin +5

Distilling demonstration effects into hidden-space interventions offers a lightweight alternative to full finetuning. However, existing multimodal variants are mostly evaluated on…

cs.CL2026

A Systematic Study of Training-Free Methods for Trustworthy Large Language Models

Wai Man Si, Mingjie Li, Michael Backes +1

As Large Language Models (LLMs) receive increasing attention and are being deployed across various domains, their potential risks, including generating harmful or biased content, p…

cs.LG2026

Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs

Wai Man Si, Mingjie Li, Michael Backes +1

Machine learning models are increasingly deployed in real-world applications, but even aligned models such as Mistral and LLaVA still exhibit unsafe behaviors inherited from pre-tr…

cs.CV2026

When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm

Ye Leng, Junjie Chu, Mingjie Li +5

Recently, multimodal large language models (MLLMs) have emerged as a unified paradigm for language and image generation. Compared with diffusion models, MLLMs possess a much strong…

cs.LG2026

Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs

Yukun Jiang, Hai Huang, Mingjie Li +3

By introducing routers to selectively activate experts in Transformer layers, the mixture-of-experts (MoE) architecture significantly reduces computational costs in large language…