3 papers
cs.CV2025
Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models
Jinyeong Kim, Seil Kang, Jiwoo Park +2
Large Vision-Language Models (LVLMs) answer visual questions by transferring information from images to text through a series of attention heads. While this image-to-text informati…
cs.LG2025
Backbone Augmented Training for Adaptations
Jae Wan Park, Junhyeok Kim, Youngjun Jun +2
Adaptations facilitate efficient training of large backbone models, including diffusion models for image generation and transformer-based language models. While various adaptation…
cs.CV2025
See What You Are Told: Visual Attention Sink in Large Multimodal Models
Seil Kang, Jinyeong Kim, Junhyeok Kim +1
Large multimodal models (LMMs) "see" images by leveraging the attention mechanism between text and visual tokens in the transformer decoder. Ideally, these models should focus on k…