What's in the Image? A Deep-Dive into the Vision of Vision Language Models
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:FUMMT2QMrecord.jsonopen to challenge →
read the original abstract
Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in comprehending complex visual content. However, the mechanisms underlying how VLMs process visual information remain largely unexplored. In this paper, we conduct a thorough empirical analysis, focusing on attention modules across layers. We reveal several key insights about how these models process visual data: (i) the internal representation of the query tokens (e.g., representations of "describe the image"), is utilized by VLMs to store global image information; we demonstrate that these models generate surprisingly descriptive responses solely from these tokens, without direct access to image tokens. (ii) Cross-modal information flow is predominantly influenced by the middle layers (approximately 25% of all layers), while early and late layers contribute only marginally.(iii) Fine-grained visual attributes and object details are directly extracted from image tokens in a spatially localized manner, i.e., the generated tokens associated with a specific object or attribute attend strongly to their corresponding regions in the image. We propose novel quantitative evaluation to validate our observations, leveraging real-world complex visual scenes. Finally, we demonstrate the potential of our findings in facilitating efficient visual processing in state-of-the-art VLMs.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
Vision-Default, Prior-Override: Causal Mechanisms of Perception-Knowledge Conflict in Vision-Language Models
VLMs default to visual grounding but a sparse circuit of 2.5-4.8% attention heads in later layers mediates prior-knowledge overrides, identified causally via patching and ablation across three model families.
-
Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders
A lightweight Q-Former proxy trained on VLM hidden states reveals that localization signals peak in input-dependent intermediate layers, not the final layers used by standard editing pipelines.
-
Counting to Four is still a Chore for VLMs
VLMs fail at counting because visual evidence degrades in later language layers, and a lightweight Modality Attention Share intervention can encourage better use of image information during answer generation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.