# Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach

arXiv: https://arxiv.org/abs/2412.18108 · HTML: https://mlsanity.com/paper/2412.18108/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 43 of its 61 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 30 of 43)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension](https://mlsanity.com/paper/2307.16125/) (2023)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering](https://mlsanity.com/paper/2305.10415/) (2023)
- [PandaGPT: One Model To Instruction-Follow Them All](https://mlsanity.com/paper/2305.16355/) (2023)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision](https://mlsanity.com/paper/2309.14181/) (2023)
- [Retrieval Head Mechanistically Explains Long-Context Factuality](https://mlsanity.com/paper/2404.15574/) (2024)
- [Video Understanding with Large Language Models: A Survey](https://mlsanity.com/paper/2312.17432/) (2023)
- [X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages](https://mlsanity.com/paper/2305.04160/) (2023)
- [DetGPT: Detect What You Need via Reasoning](https://mlsanity.com/paper/2305.14167/) (2023)
- [From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models](https://mlsanity.com/paper/2310.08825/) (2023)
- [Information Flow Routes: Automatically Interpreting Language Models at Scale](https://mlsanity.com/paper/2403.00824/) (2024)

## Built on by (most cited first, 30 of 35)

- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)](https://mlsanity.com/paper/2504.03151/) (2025)
- [Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding](https://mlsanity.com/paper/2509.23050/) (2025)
- [Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping](https://mlsanity.com/paper/2510.09741/) (2025)
- [Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting](https://mlsanity.com/paper/2504.05541/) (2025)
- [How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads](https://mlsanity.com/paper/2505.15865/) (2025)
- [Multi-speaker Attention Alignment for Multimodal Social Interaction](https://mlsanity.com/paper/2511.17952/) (2025)
- [How Vision Becomes Language: A Layer-wise Information-Theoretic Analysis of Multimodal Reasoning](https://mlsanity.com/paper/2602.15580/) (2026)
- [Detecting Misbehaviors of Large Vision-Language Models by Evidential Uncertainty Quantification](https://mlsanity.com/paper/2602.05535/) (2026)
- [MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness](https://mlsanity.com/paper/2505.20426/) (2025)
- [Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Models](https://mlsanity.com/paper/2512.15885/) (2025)
- [Reallocating Attention Across Layers to Reduce Multimodal Hallucination](https://mlsanity.com/paper/2510.10285/) (2025)
- [Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection](https://mlsanity.com/paper/2602.24021/) (2026)
- [Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads](https://mlsanity.com/paper/2606.05843/) (2026)
- [Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models](https://mlsanity.com/paper/2503.00059/) (2025)
- [CAI: Caption-Sensitive Attention Intervention for Mitigating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2506.23590/) (2025)
- [When to Think and When to Look: Uncertainty-Guided Lookback](https://mlsanity.com/paper/2511.15613/) (2025)
- [ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting](https://mlsanity.com/paper/2603.23186/) (2026)
- [Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs](https://mlsanity.com/paper/2509.08016/) (2025)
- [PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing](https://mlsanity.com/paper/2510.07452/) (2025)
- [Investigating The Functional Roles of Attention Heads in Vision Language Models: Evidence for Reasoning Modules](https://mlsanity.com/paper/2512.10300/) (2025)
- [Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers](https://mlsanity.com/paper/2603.02919/) (2026)
- [Look Twice: Training-Free Evidence Highlighting for Knowledge-based Visual Question Answering](https://mlsanity.com/paper/2604.01280/) (2026)
- [Head-wise Modality Specialization within MLLMs for Robust Fake News Detection under Missing Modality](https://mlsanity.com/paper/2604.09711/) (2026)
- [TraversalBench: Challenging Paths to Follow for Vision Language Models](https://mlsanity.com/paper/2604.10999/) (2026)
- [MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues](https://mlsanity.com/paper/2605.21954/) (2026)
- [Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models](https://mlsanity.com/paper/2605.27243/) (2026)
- [AdaCount: Training-Free Similarity-Guided Spatial and Feature Adaptation for Zero-Shot Object Counting](https://mlsanity.com/paper/2607.02139/) (2026)
- [When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities](https://mlsanity.com/paper/2607.08605/) (2026)
- [Knowing Isn't Always Saying: When Do Spatial Encodings Reach Answers in Vision-Language Models?](https://mlsanity.com/paper/2608.22916/) (2026)

## Abstract (arXiv)

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.