# Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs

arXiv: https://arxiv.org/abs/2503.02597 · HTML: https://mlsanity.com/paper/2503.02597/

## Key facts

- Cited by 7 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 42 of its 56 references that are in the map.
- First posted on arXiv 4 Mar 2025.

## 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 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension](https://mlsanity.com/paper/2307.16125/) (2023)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [DataComp: In search of the next generation of multimodal datasets](https://mlsanity.com/paper/2304.14108/) (2023)
- [DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding](https://mlsanity.com/paper/2412.10302/) (2024)
- [OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models](https://mlsanity.com/paper/2308.01390/) (2023)

## Built on by (most cited first, 7 of 7)

- [CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting](https://mlsanity.com/paper/2504.15485/) (2025)
- [Multi-speaker Attention Alignment for Multimodal Social Interaction](https://mlsanity.com/paper/2511.17952/) (2025)
- [SF-Mamba: Rethinking State Space Model for Vision](https://mlsanity.com/paper/2603.16423/) (2026)
- [Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow](https://mlsanity.com/paper/2604.15809/) (2026)
- [VIRTUE: Visual-Interactive Text-Image Universal Embedder](https://mlsanity.com/paper/2510.00523/) (2025)
- [Counting Through Occlusion: Framework for Open World Amodal Counting](https://mlsanity.com/paper/2511.12702/) (2025)
- [RAVE: Re-Allocating Visual Attention in Large Multimodal Models](https://mlsanity.com/paper/2605.18359/) (2026)

## Abstract (arXiv)

Recent Multimodal Large Language Models (MLLMs) have demonstrated significant progress in perceiving and reasoning over multimodal inquiries, ushering in a new research era for foundation models. However, vision-language misalignment in MLLMs has emerged as a critical challenge, where the textual responses generated by these models are not factually aligned with the given text-image inputs. Existing efforts to address vision-language misalignment have focused on developing specialized vision-language connectors or leveraging visual instruction tuning from diverse domains. In this paper, we tackle this issue from a fundamental yet unexplored perspective by revisiting the core architecture of MLLMs. Most MLLMs are typically built on decoder-only LLMs consisting of a causal attention mechanism, which limits the ability of the earlier modalities (e.g., images) to incorporate information from the latter modalities (e.g., text). To address this problem a MLLM that unlocks causal attention into our proposed modality-mutual attention (MMA) to enable image tokens to attend to text tokens. This simple yet effective design allows MMA to achieve state-of-the-art performance in 12 multimodal understanding benchmarks (+6.2% on average across 3 LLMs backbones) without introducing additional parameters. Our MMA design is intended to be generic, allowing for applications across various modalities, and scalable to accommodate diverse multimodal scenarios.