# Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties

arXiv: https://arxiv.org/abs/2311.17041 · HTML: https://mlsanity.com/paper/2311.17041/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 41 of its 55 references that are in the map.
- First posted on arXiv 28 Nov 2023.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 30 of 41)

- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [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)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [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)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [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)
- [Language Is Not All You Need: Aligning Perception with Language Models](https://mlsanity.com/paper/2302.14045/) (2023)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [MetaICL: Learning to Learn In Context](https://mlsanity.com/paper/2110.15943/) (2021)
- [OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents](https://mlsanity.com/paper/2306.16527/) (2023)

## Built on by (most cited first, 21 of 21)

- [Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey](https://mlsanity.com/paper/2412.18619/) (2024)
- [Sakuga-42M Dataset: Scaling Up Cartoon Research](https://mlsanity.com/paper/2405.07425/) (2024)
- [VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding](https://mlsanity.com/paper/2412.02186/) (2024)
- [Question-Answering Dense Video Events](https://mlsanity.com/paper/2409.04388/) (2024)
- [Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation](https://mlsanity.com/paper/2410.01341/) (2024)
- [Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern Transformers](https://mlsanity.com/paper/2601.20796/) (2026)
- [AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models](https://mlsanity.com/paper/2503.08417/) (2025)
- [Towards Accurate Emotion-Attributed Video Captioning via Fine-grained Emotion-Cause Pair Extraction](https://mlsanity.com/paper/2606.08566/) (2026)
- [Memory Helps, but Confabulation Misleads: Understanding Streaming Events in Videos with MLLMs](https://mlsanity.com/paper/2502.15457/) (2025)
- [Q-Adapter: Visual Query Adapter for Extracting Textually-related Features in Video Captioning](https://mlsanity.com/paper/2510.10022/) (2025)
- [Personal Visual Context Learning in Large Multimodal Models](https://mlsanity.com/paper/2605.10936/) (2026)
- [Espresso: High Compression For Rich Extraction From Videos for Your Vision-Language Model](https://mlsanity.com/paper/2412.04729/) (2024)
- [Linking Perception, Confidence and Accuracy in MLLMs](https://mlsanity.com/paper/2603.12149/) (2026)
- [FILS: Self-Supervised Video Feature Prediction In Semantic Language Space](https://mlsanity.com/paper/2406.03447/) (2024)
- [Punching Bag vs. Punching Person: Motion Transferability in Videos](https://mlsanity.com/paper/2508.00085/) (2025)
- [Temporally-Grounded Language Generation: Towards Real-Time Vision-Language Models](https://mlsanity.com/paper/2505.11326/) (2025)
- [Robust Egocentric Visual Attention Prediction Through Language-guided Scene Context-aware Learning](https://mlsanity.com/paper/2601.01818/) (2026)
- [From Frames to Temporal Graphs: In-Context Egocentric Action Recognition with Vision-Language Models](https://mlsanity.com/paper/2606.15417/) (2026)
- [Personalized Object Identification and Localization via In-Context Inference with Vision-Language Models](https://mlsanity.com/paper/2607.00357/) (2026)
- [AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models](https://mlsanity.com/paper/2607.02269/) (2026)
- [Causal-EVC: Breaking Emotional Spurious Causality via Spatiotemporal Grounding and Counterfactual Intervention](https://mlsanity.com/paper/2609.36776/) (2026)

## Abstract (arXiv)

A major reason behind the recent success of large language models (LLMs) is their textitin-context learning capability, which makes it possible to rapidly adapt them to downstream text-based tasks by prompting them with a small number of relevant demonstrations. While large vision-language models (VLMs) have recently been developed for tasks requiring both text and images, they largely lack in-context learning over visual information, especially in understanding and generating text about videos. In this work, we implement Emergent In-context Learning on Videos (eilev), a novel training paradigm that induces in-context learning over video and text by capturing key properties of pre-training data found by prior work to be essential for in-context learning in transformers. In our experiments, we show that eilev-trained models outperform other off-the-shelf VLMs in few-shot video narration for novel, rare actions. Furthermore, we demonstrate that these key properties of bursty distributions, skewed marginal distributions, and dynamic meaning each contribute to varying degrees to VLMs' in-context learning capability in narrating procedural videos. Our results, analysis, and eilev-trained models yield numerous insights about the emergence of in-context learning over video and text, creating a foundation for future work to optimize and scale VLMs for open-domain video understanding and reasoning. Our code and demo are available at urlhttps://github.com/yukw777/EILEV.