4 papers
Attention-space Contrastive Guidance for Efficient Hallucination Mitigation in LVLMs
Yujin Jo, Sangyoon Bae, Taesup Kim
Hallucinations in large vision--language models (LVLMs) often arise when language priors dominate over visual evidence, leading to object misidentification and visually inconsisten…
Memory-Free Continual Learning with Null Space Adaptation for Zero-Shot Vision-Language Models
Yujin Jo, Taesup Kim
Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalization, enabling deployment in a wide range of real-world tasks without addi…
Retaining and Enhancing Pre-trained Knowledge in Vision-Language Models with Prompt Ensembling
Donggeun Kim, Yujin Jo, Myungjoo Lee +1
The advancement of vision-language models, particularly the Contrastive Language-Image Pre-training (CLIP) model, has revolutionized the field of machine learning by enabling robus…
Missing Modality Prediction for Unpaired Multimodal Learning via Joint Embedding of Unimodal Models
Donggeun Kim, Taesup Kim
Multimodal learning typically relies on the assumption that all modalities are fully available during both the training and inference phases. However, in real-world scenarios, cons…