Internal visual-text alignment in MLLMs is best read as a geometric diagnostic of the visual stream inside the language model rather than a direct proxy for content-level cross-modal interaction, and is most informative when calibrated by controlled task evidence.
Abstract
Layer-wise visual-text similarity in Multimodal Large Language Models (MLLMs) is widely interpreted as evidence that the language model progressively integrates visual content into a shared representation space. This reading rests on the assumption that scalar alignment scores reflect content-level cross-modal interaction. To test this assumption, we apply controlled interventions to the visual stream. Across 13 MLLMs from five families spanning 0.5B to 72B parameters, replacing projector-output visual tokens with Gaussian noise sharply reduces task accuracy, yet four standard scalar measures (CKA, SVCCA, MIR, and the leading principal-angle cosine) fail to consistently separate the corrupted stream from the original. We call this failure the alignment illusion and trace it to the shared language-model pathway: anisotropic MLP down-projections pull visual and text tokens toward common output directions, producing weight-induced alignment. Because this component is essentially one-dimensional, we introduce the principal-angle gap (PA gap), defined as the difference between the top two principal-angle cosines, which separates weight-induced similarity from multi-directional visual structure. Under graded visual corruption, the PA gap tracks task accuracy more consistently than the scalar scores we consider; under a structured but irrelevant image, it further exposes regimes in which internal geometry and task accuracy come apart. Internal visual-text alignment in MLLMs is therefore best read as a geometric diagnostic of the visual stream inside the language model rather than a direct proxy for content-level cross-modal interaction, and is most informative when calibrated by controlled task evidence.
Vision-of-Thought (VoT), a framework that introduces a discrete visual-thinking layer between vision-language models (VLMs) and diffusion transformers (DiTs) that improves semantic alignment and provides a structured interface for interpretable and controllable generation is proposed.
Jingxiang Sun, Chao Liao, Zheng-Xiong Luo et al.· 0 citations
This work proposes $\delta$-Vision, which replaces repeated Transformer evolution of visual tokens with lightweight low-rank adapters that construct layer-wise visual memories while preserving all visual tokens for text retrieval, and achieves higher accuracy than visual token pruning baselines at comparable or lower c...
Jing-Di Lei, Junxian Li, Di Zhang et al.· arXiv.org· 0 citations
These metrics and case study offer empirical observations that could help inform data selection and script adaptation choices when working with pixel-based models in similar low-resource settings.
Ran Zhang, Miryam de Lhoneux, Wessel Poelman· 0 citations
By clarifying when and why gap modification changes model behavior, this account provides a principled basis for selecting gap interventions in similarity-based vision-language systems across evaluated downstream tasks.
LookBack, a training-free LVLM response scoring method that augments token likelihood with visual lookback score, a lightweight measure of how strongly each response token refers to image tokens, consistently improves Best-of-$N$ selection over existing baselines with negligible additional overhead.
Beomsik Cho, Jin-Ha Kim, Dongseok Lee et al.· 0 citations
Dual-encoder vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a “modality gap phenomenon” meaning there exists a clear separation between the embeddings from one modality and another in the embedding space. While...
François Role, Sébastien Meyer, Victor Amblard· International Journal of Mul...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 28, 2026
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
Microsoft Research Blog· microsoft.comAug 11, 2026
Radiology AI is evolving beyond report generation. CARE-X explores a unified approach that combines flexible reasoning, calibrated predictions, and measurement-based tools for chest X-ray interpretation. The post Introducing CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement appeared first on Microsoft Research.