# What do vision-language models see in the context? Investigating multimodal in-context learning

arXiv: https://arxiv.org/abs/2510.24331 · HTML: https://mlsanity.com/paper/2510.24331/

## Key facts

- Cited by 4 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 27 of its 46 references that are in the map.
- First posted on arXiv 28 Oct 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, 27 of 27)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [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)
- [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022)
- [nocaps: novel object captioning at scale](https://mlsanity.com/paper/1812.08658/) (2018)
- [PandaGPT: One Model To Instruction-Follow Them All](https://mlsanity.com/paper/2305.16355/) (2023)
- [mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding](https://mlsanity.com/paper/2403.12895/) (2024)
- [Honeybee: Locality-enhanced Projector for Multimodal LLM](https://mlsanity.com/paper/2312.06742/) (2023)
- [MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning](https://mlsanity.com/paper/2309.07915/) (2023)
- [LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token](https://mlsanity.com/paper/2501.03895/) (2025)
- [Grounding Language Models to Images for Multimodal Inputs and Outputs](https://mlsanity.com/paper/2301.13823/) (2023)
- [From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning](https://mlsanity.com/paper/2310.00492/) (2023)
- [What Makes Multimodal In-Context Learning Work?](https://mlsanity.com/paper/2404.15736/) (2024)
- [eP-ALM: Efficient Perceptual Augmentation of Language Models](https://mlsanity.com/paper/2303.11403/) (2023)
- [What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration](https://mlsanity.com/paper/2410.20482/) (2024)
- [LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model Prompting](https://mlsanity.com/paper/2305.19821/) (2023)

## Built on by (most cited first, 4 of 4)

- [Linking Perception, Confidence and Accuracy in MLLMs](https://mlsanity.com/paper/2603.12149/) (2026)
- [Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection](https://mlsanity.com/paper/2603.24181/) (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)

## Abstract (arXiv)

In-context learning (ICL) enables Large Language Models (LLMs) to learn tasks from demonstration examples without parameter updates. Although it has been extensively studied in LLMs, its effectiveness in Vision-Language Models (VLMs) remains underexplored. In this work, we present a systematic study of ICL in VLMs, evaluating seven models spanning four architectures on three image captioning benchmarks. We analyze how prompt design, architectural choices, and training strategies influence multimodal ICL. To our knowledge, we are the first to analyze how attention patterns in VLMs vary with an increasing number of in-context demonstrations. Our results reveal that training on imag-text interleaved data enhances ICL performance but does not imply effective integration of visual and textual information from demonstration examples. In contrast, instruction tuning improves instruction-following but can reduce reliance on in-context demonstrations, suggesting a trade-off between instruction alignment and in-context adaptation. Attention analyses further show that current VLMs primarily focus on textual cues and fail to leverage visual information, suggesting a limited capacity for multimodal integration. These findings highlight key limitations in the ICL abilities of current VLMs and provide insights for enhancing their ability to learn from multimodal in-context examples.