Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach
This work provides insights into multimodal adaptation in AI systems, though it is incremental in analyzing existing models rather than introducing new capabilities.
The paper investigated how language models process visual content by analyzing attention heads across multiple model families and scales, identifying a unique class of attention heads that specifically focus on visual tokens and correlating their behavior with attention weight distributions.
Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable progress in visual understanding. This impressive leap raises a compelling question: how can language models, initially trained solely on linguistic data, effectively interpret and process visual content? This paper aims to address this question with systematic investigation across 4 model families and 4 model scales, uncovering a unique class of attention heads that focus specifically on visual content. Our analysis reveals a strong correlation between the behavior of these attention heads, the distribution of attention weights, and their concentration on visual tokens within the input. These findings enhance our understanding of how LLMs adapt to multimodal tasks, demonstrating their potential to bridge the gap between textual and visual understanding. This work paves the way for the development of AI systems capable of engaging with diverse modalities.