# Towards Multimodal In-Context Learning for Vision & Language Models

arXiv: https://arxiv.org/abs/2403.12736 · HTML: https://mlsanity.com/paper/2403.12736/

## Key facts

- Cited by 25 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 51 of its 65 references that are in the map.
- First posted on arXiv 19 Mar 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 51)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [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)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [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)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension](https://mlsanity.com/paper/2307.16125/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning](https://mlsanity.com/paper/2310.09478/) (2023)
- [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, 25 of 25)

- [Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning](https://mlsanity.com/paper/2406.15334/) (2024)
- [MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models](https://mlsanity.com/paper/2408.01337/) (2024)
- [What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration](https://mlsanity.com/paper/2410.20482/) (2024)
- [SketchAgent: Language-Driven Sequential Sketch Generation](https://mlsanity.com/paper/2411.17673/) (2024)
- [ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs](https://mlsanity.com/paper/2406.08164/) (2024)
- [True Multimodal In-Context Learning Needs Attention to the Visual Context](https://mlsanity.com/paper/2507.15807/) (2025)
- [The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective](https://mlsanity.com/paper/2407.08583/) (2024)
- [XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning](https://mlsanity.com/paper/2406.08973/) (2024)
- [Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features](https://mlsanity.com/paper/2412.00142/) (2024)
- [QCalEval: Benchmarking Vision-Language Models for Quantum Calibration Plot Understanding](https://mlsanity.com/paper/2604.25884/) (2026)
- [SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization](https://mlsanity.com/paper/2411.11909/) (2024)
- [TTRV: Test-Time Reinforcement Learning for Vision Language Models](https://mlsanity.com/paper/2510.06783/) (2025)
- [GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models](https://mlsanity.com/paper/2410.06154/) (2024)
- [Teaching VLMs to Localize Specific Objects from In-context Examples](https://mlsanity.com/paper/2411.13317/) (2024)
- [Generalizable Object Re-Identification via Visual In-Context Prompting](https://mlsanity.com/paper/2508.21222/) (2025)
- [PRISMM-Bench: A Benchmark of Peer-Review Grounded Multimodal Inconsistencies](https://mlsanity.com/paper/2510.16505/) (2025)
- [Personal Visual Context Learning in Large Multimodal Models](https://mlsanity.com/paper/2605.10936/) (2026)
- [Enhancing Explainability in Multimodal Large Language Models Using Ontological Context](https://mlsanity.com/paper/2409.18753/) (2024)
- [CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models](https://mlsanity.com/paper/2503.14161/) (2025)
- [Spoken Language Understanding on Unseen Tasks With In-Context Learning](https://mlsanity.com/paper/2505.07731/) (2025)
- [HAIBU-ReMUD: Reasoning Multimodal Ultrasound Dataset and Model Bridging to General Specific Domains](https://mlsanity.com/paper/2506.07837/) (2025)
- [When Is a Task Vector Enough? An Empirical Theory of Implicit Multimodal ICL](https://mlsanity.com/paper/2608.13385/) (2026)
- [Taming Visual Neglect: A Variational Information Bottleneck Framework for Adaptive Attention in Multimodal In-Context Learning](https://mlsanity.com/paper/2608.23570/) (2026)
- [Gender Bias in Vision-Language In-Context Learning](https://mlsanity.com/paper/2609.27682/) (2026)
- [Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning](https://mlsanity.com/paper/2610.01936/) (2026)

## Abstract (arXiv)

State-of-the-art Vision-Language Models (VLMs) ground the vision and the language modality primarily via projecting the vision tokens from the encoder to language-like tokens, which are directly fed to the Large Language Model (LLM) decoder. While these models have shown unprecedented performance in many downstream zero-shot tasks (eg image captioning, question answers, etc), still little emphasis has been put on transferring one of the core LLM capability of In-Context Learning (ICL). ICL is the ability of a model to reason about a downstream task with a few examples demonstrations embedded in the prompt. In this work, through extensive evaluations, we find that the state-of-the-art VLMs somewhat lack the ability to follow ICL instructions. In particular, we discover that even models that underwent large-scale mixed modality pre-training and were implicitly guided to make use of interleaved image and text information (intended to consume helpful context from multiple images) under-perform when prompted with few-shot demonstrations (in an ICL way), likely due to their lack of direct ICL instruction tuning. To enhance the ICL abilities of the present VLM, we propose a simple yet surprisingly effective multi-turn curriculum-based learning methodology with effective data mixes, leading up to a significant 21.03% (and 11.3% on average) ICL performance boost over the strongest VLM baselines and a variety of ICL benchmarks. Furthermore, we also contribute new benchmarks for ICL evaluation in VLMs and discuss their advantages over the prior art.