# Many-Shot In-Context Learning in Multimodal Foundation Models

arXiv: https://arxiv.org/abs/2405.09798 · HTML: https://mlsanity.com/paper/2405.09798/

## Key facts

- Cited by 67 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 40 references that are in the map.
- First posted on arXiv 16 May 2024.

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark](https://mlsanity.com/paper/1909.00133/) (2019)
- [Many-Shot In-Context Learning](https://mlsanity.com/paper/2404.11018/) (2024)
- [RSVQA: Visual Question Answering for Remote Sensing Data](https://mlsanity.com/paper/2003.07333/) (2020)
- [MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning](https://mlsanity.com/paper/2309.07915/) (2023)
- [In-Context Learning with Long-Context Models: An In-Depth Exploration](https://mlsanity.com/paper/2405.00200/) (2024)
- [Contextual Object Detection with Multimodal Large Language Models](https://mlsanity.com/paper/2305.18279/) (2023)
- [Learning from Few Examples: A Summary of Approaches to Few-Shot Learning](https://mlsanity.com/paper/2203.04291/) (2022)
- [Batch Prompting: Efficient Inference with Large Language Model APIs](https://mlsanity.com/paper/2301.08721/) (2023)
- [DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations](https://mlsanity.com/paper/2201.09637/) (2022)
- [DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM](https://mlsanity.com/paper/2403.12488/) (2024)
- [Self-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations](https://mlsanity.com/paper/2305.15035/) (2023)
- [In-Context Learning with Many Demonstration Examples](https://mlsanity.com/paper/2302.04931/) (2023)
- [On the Out-Of-Distribution Generalization of Multimodal Large Language Models](https://mlsanity.com/paper/2402.06599/) (2024)
- [Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?](https://mlsanity.com/paper/2402.11597/) (2024)
- [How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation](https://mlsanity.com/paper/2312.07424/) (2023)
- [BatchPrompt: Accomplish more with less](https://mlsanity.com/paper/2309.00384/) (2023)
- [CliqueParcel: An Approach For Batching LLM Prompts That Jointly Optimizes Efficiency And Faithfulness](https://mlsanity.com/paper/2402.14833/) (2024)

## Built on by (most cited first, 30 of 67)

- [LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models](https://mlsanity.com/paper/2407.07895/) (2024)
- [MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding](https://mlsanity.com/paper/2406.09411/) (2024)
- [MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents](https://mlsanity.com/paper/2501.14654/) (2025)
- [Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning](https://mlsanity.com/paper/2406.15334/) (2024)
- [A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualization](https://mlsanity.com/paper/2411.06018/) (2024)
- [LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations](https://mlsanity.com/paper/2412.01441/) (2024)
- [Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey](https://mlsanity.com/paper/2412.18619/) (2024)
- [Leveraging Vision Language Models for Specialized Agricultural Tasks](https://mlsanity.com/paper/2407.19617/) (2024)
- [Identifying and Mitigating Position Bias of Multi-image Vision-Language Models](https://mlsanity.com/paper/2503.13792/) (2025)
- [From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation](https://mlsanity.com/paper/2502.00330/) (2025)
- [VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-use](https://mlsanity.com/paper/2410.16400/) (2024)
- [VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding](https://mlsanity.com/paper/2412.02186/) (2024)
- [True Multimodal In-Context Learning Needs Attention to the Visual Context](https://mlsanity.com/paper/2507.15807/) (2025)
- [How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks](https://mlsanity.com/paper/2507.01955/) (2025)
- [Vector-ICL: In-context Learning with Continuous Vector Representations](https://mlsanity.com/paper/2410.05629/) (2024)
- [MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning](https://mlsanity.com/paper/2505.16225/) (2025)
- [WONDERBREAD: A Benchmark for Evaluating Multimodal Foundation Models on Business Process Management Tasks](https://mlsanity.com/paper/2406.13264/) (2024)
- [Visual RAG: Expanding MLLM visual knowledge without fine-tuning](https://mlsanity.com/paper/2501.10834/) (2025)
- [QCalEval: Benchmarking Vision-Language Models for Quantum Calibration Plot Understanding](https://mlsanity.com/paper/2604.25884/) (2026)
- [MIR-Bench: Can Your LLM Recognize Complicated Patterns via Many-Shot In-Context Reasoning?](https://mlsanity.com/paper/2502.09933/) (2025)
- [Efficient Multi-modal Long Context Learning for Training-free Adaptation](https://mlsanity.com/paper/2505.19812/) (2025)
- [Large (Vision) Language Models are Unsupervised In-Context Learners](https://mlsanity.com/paper/2504.02349/) (2025)
- [Zoomer: Adaptive Image Focus Optimization for Black-box MLLM](https://mlsanity.com/paper/2505.00742/) (2025)
- [Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs](https://mlsanity.com/paper/2506.03195/) (2025)
- [Retrieval-augmented in-context learning for multimodal large language models in disease classification](https://mlsanity.com/paper/2505.02087/) (2025)
- [Uncertainty Unveiled: Can Exposure to More In-context Examples Mitigate Uncertainty for Large Language Models?](https://mlsanity.com/paper/2505.21003/) (2025)
- [Adapting Large Multimodal Models to Distribution Shifts: The Role of In-Context Learning](https://mlsanity.com/paper/2405.12217/) (2024)
- [Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context Learning](https://mlsanity.com/paper/2511.08246/) (2025)
- [Auto-Demo Prompting: Leveraging Generated Outputs as Demonstrations for Enhanced Batch Prompting](https://mlsanity.com/paper/2410.01724/) (2024)
- [In-context Learning in Presence of Spurious Correlations](https://mlsanity.com/paper/2410.03140/) (2024)

## Abstract (arXiv)

Large language models are effective at few-shot in-context learning (ICL). Recent advancements in multimodal foundation models have enabled unprecedentedly long context windows, presenting an opportunity to explore their capability to perform ICL with many more demonstrating examples. In this work, we evaluate the performance of multimodal foundation models scaling from few-shot to many-shot ICL. We benchmark GPT-4o and Gemini 1.5 Pro across 14 datasets spanning multiple domains (natural imagery, medical imagery, remote sensing, and molecular imagery) and tasks (image classification, visual QA, and object localization). We observe that many-shot ICL, including up to almost 2,000 demonstrating examples, leads to substantial improvements compared to few-shot (<100 examples) ICL across all of the datasets. Further, Gemini 1.5 Pro performance continues to improve log-linearly up to the maximum number of tested examples on many datasets. We also find open-weights multimodal foundation models like Llama 3.2-Vision do not benefit from the demonstrating examples, highlighting an important gap between open and closed multimodal foundation models. Given the high inference costs required for many-shot ICL, we also explore the impact of batching multiple queries in a single API call. We show that batching up to 50 queries can lead to performance improvements under zero-shot and many-shot ICL, with substantial gains in the zero-shot setting on multiple datasets, while drastically reducing per-query cost and latency. Finally, while GPT-4o and Gemini 1.5 Pro achieve similar zero-shot performance across the datasets, Gemini 1.5 Pro learns more quickly than GPT-4o on most datasets. Our results suggest that many-shot ICL could enable users to efficiently adapt multimodal foundation models to new applications and domains. Our codebase is publicly available at https://github.com/stanfordmlgroup/ManyICL .