# True Multimodal In-Context Learning Needs Attention to the Visual Context

arXiv: https://arxiv.org/abs/2507.15807 · HTML: https://mlsanity.com/paper/2507.15807/

## Key facts

- Cited by 16 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 47 references that are in the map.
- First posted on arXiv 21 Jul 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)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [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)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models](https://mlsanity.com/paper/2308.01390/) (2023)
- [Otter: A Multi-Modal Model with In-Context Instruction Tuning](https://mlsanity.com/paper/2305.03726/) (2023)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [What matters when building vision-language models?](https://mlsanity.com/paper/2405.02246/) (2024)
- [An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA](https://mlsanity.com/paper/2109.05014/) (2021)
- [MIMIC-IT: Multi-Modal In-Context Instruction Tuning](https://mlsanity.com/paper/2306.05425/) (2023)
- [MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs](https://mlsanity.com/paper/2502.17422/) (2025)
- [Building and better understanding vision-language models: insights and future directions](https://mlsanity.com/paper/2408.12637/) (2024)
- [MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning](https://mlsanity.com/paper/2309.07915/) (2023)
- [What In-Context Learning "Learns" In-Context: Disentangling Task Recognition and Task Learning](https://mlsanity.com/paper/2305.09731/) (2023)
- [Many-Shot In-Context Learning in Multimodal Foundation Models](https://mlsanity.com/paper/2405.09798/) (2024)
- [A Survey on LoRA of Large Language Models](https://mlsanity.com/paper/2407.11046/) (2024)
- [Exploring Diverse In-Context Configurations for Image Captioning](https://mlsanity.com/paper/2305.14800/) (2023)
- [Learning to Retrieve In-Context Examples for Large Language Models](https://mlsanity.com/paper/2307.07164/) (2023)
- [What Makes Multimodal In-Context Learning Work?](https://mlsanity.com/paper/2404.15736/) (2024)
- [MIBench: Evaluating Multimodal Large Language Models over Multiple Images](https://mlsanity.com/paper/2407.15272/) (2024)
- [In-context learning enables multimodal large language models to classify cancer pathology images](https://mlsanity.com/paper/2403.07407/) (2024)
- [Low-Rank Adaptation for Foundation Models: A Comprehensive Review](https://mlsanity.com/paper/2501.00365/) (2024)
- [Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?](https://mlsanity.com/paper/2311.18021/) (2023)
- [How to Configure Good In-Context Sequence for Visual Question Answering](https://mlsanity.com/paper/2312.01571/) (2023)

## Built on by (most cited first, 16 of 16)

- [Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs](https://mlsanity.com/paper/2606.26387/) (2026)
- [Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern Transformers](https://mlsanity.com/paper/2601.20796/) (2026)
- [Online In-Context Distillation for Low-Resource Vision Language Models](https://mlsanity.com/paper/2510.18117/) (2025)
- [Multimodal In-context Learning for ASR of Low-resource Languages](https://mlsanity.com/paper/2601.05707/) (2026)
- [Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks](https://mlsanity.com/paper/2604.13403/) (2026)
- [Enhancing Multimodal In-Context Learning via Inductive-Deductive Reasoning](https://mlsanity.com/paper/2605.02378/) (2026)
- [HIFICL: High-Fidelity In-Context Learning for Multimodal Tasks](https://mlsanity.com/paper/2603.12760/) (2026)
- [Few-shot Writer Adaptation via Multimodal In-Context Learning](https://mlsanity.com/paper/2603.29450/) (2026)
- [Ego: Embedding-Guided Personalization of Vision-Language Models](https://mlsanity.com/paper/2603.09771/) (2026)
- [Sci-Rho: A Multilingual Visually-Grounded Symbolic Benchmark for STEM Problems](https://mlsanity.com/paper/2606.08034/) (2026)
- [Criterion-Conditional In-Context Learning: Evaluating Criterion-Shift Adaptation in Vision-Language Models](https://mlsanity.com/paper/2607.02575/) (2026)
- [Taming Visual Neglect: A Variational Information Bottleneck Framework for Adaptive Attention in Multimodal In-Context Learning](https://mlsanity.com/paper/2608.23570/) (2026)
- [TwinICL: Diagnosing Multimodal In-Context Learning through Paired Counterfactuals](https://mlsanity.com/paper/2609.15028/) (2026)
- [MCD: Causal Distillation of Multimodal In-Context Learning in Large Vision-Language Models](https://mlsanity.com/paper/2609.39920/) (2026)
- [In-Context Learning Can Help Vision-Language Models Overcome Training Priors](https://mlsanity.com/paper/2610.12942/) (2026)
- [ActICL: Post-Training for Agentic Multimodal In-Context Learning](https://mlsanity.com/paper/2610.19475/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs), built on powerful language backbones, have enabled Multimodal In-Context Learning (MICL)-adapting to new tasks from a few multimodal demonstrations consisting of images, questions, and answers. Despite showing noticeable improvement on standard vision-language datasets, current MLLMs struggle to leverage visual information in the demonstrations. Specifically, they tend to neglect visual cues and over-rely on textual patterns, leading to mere text imitation rather than genuine multimodal adaptation. This behavior makes MICL still unimodal and largely restricts its practical utility. More importantly, this limitation is often concealed by the improved performance on tasks that do not require understanding the visual context. As a result, how to effectively enhance MICL ability and reliably evaluate the MICL performance remains underexplored. To address these issues, we first introduce Dynamic Attention Reallocation (DARA), an efficient fine-tuning strategy that encourages models to attend to the visual context by rebalancing attention across visual and textual tokens. In addition, we present TrueMICL, an MICL-dedicated dataset with both support and test sets that explicitly requires the integration of multimodal information-particularly visual content-for correct task completion. Extensive experiments demonstrate the effectiveness of our holistic solution, showcasing substantial improvements in the true multimodal in-context learning capabilities. Code and datasets are available at https://chenxshuo.github.io/true-micl-colm .