4 papers
SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretability
Hanwei Zhang, Luo Cheng, Rui Wen +3
Explainable AI (XAI) is crucial for building transparent and trustworthy machine learning systems, especially in high-stakes domains. Concept Bottleneck Models (CBMs) have emerged…
Fake-in-Facext: Towards Fine-Grained Explainable DeepFake Analysis
Lixiong Qin, Yang Zhang, Mei Wang +3
The advancement of Multimodal Large Language Models (MLLMs) has bridged the gap between vision and language tasks, enabling the implementation of Explainable DeepFake Analysis (XDF…
Minimalist Concept Erasure in Generative Models
Yang Zhang, Er Jin, Yanfei Dong +5
Recent advances in generative models have demonstrated remarkable capabilities in producing high-quality images, but their reliance on large-scale unlabeled data has raised signifi…
PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs
Yixuan Wu, Yang Zhang, Jian Wu +2
Multimodal Large Language Models (MLLMs) excel in vision-language tasks, such as image captioning and visual question answering. However, they often suffer from over-reliance on sp…