# VideoMAP: Toward Scalable Mamba-based Video Autoregressive Pretraining

arXiv: https://arxiv.org/abs/2503.12332 · HTML: https://mlsanity.com/paper/2503.12332/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 35 of its 41 references that are in the map.
- First posted on arXiv 16 Mar 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Video, motion and generative Mamba models](https://mlsanity.com/ssm/video-motion-and-generative-mamba-models/)

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [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)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering](https://mlsanity.com/paper/1704.04497/) (2017)
- [VideoMamba: State Space Model for Efficient Video Understanding](https://mlsanity.com/paper/2403.06977/) (2024)
- [COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis](https://mlsanity.com/paper/1903.02874/) (2019)
- [Valley: Video Assistant with Large Language model Enhanced abilitY](https://mlsanity.com/paper/2306.07207/) (2023)
- [MambaVision: A Hybrid Mamba-Transformer Vision Backbone](https://mlsanity.com/paper/2407.08083/) (2024)
- [Repeat After Me: Transformers are Better than State Space Models at Copying](https://mlsanity.com/paper/2402.01032/) (2024)
- [Unmasked Teacher: Towards Training-Efficient Video Foundation Models](https://mlsanity.com/paper/2303.16058/) (2023)
- [Long Movie Clip Classification with State-Space Video Models](https://mlsanity.com/paper/2204.01692/) (2022)
- [Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks](https://mlsanity.com/paper/2402.04248/) (2024)
- [Timeception for Complex Action Recognition](https://mlsanity.com/paper/1812.01289/) (2018)
- [Learning To Recognize Procedural Activities with Distant Supervision](https://mlsanity.com/paper/2201.10990/) (2022)
- [RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval](https://mlsanity.com/paper/2402.18510/) (2024)
- [VideoGraph: Recognizing Minutes-Long Human Activities in Videos](https://mlsanity.com/paper/1905.05143/) (2019)

## Built on by (most cited first, 3 of 3)

- [UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks](https://mlsanity.com/paper/2507.11336/) (2025)
- [Universal Visuo-Tactile Video Understanding for Embodied Interaction](https://mlsanity.com/paper/2505.22566/) (2025)
- [TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining](https://mlsanity.com/paper/2609.33419/) (2026)

## Abstract (arXiv)

Recent Mamba-based architectures for video understanding demonstrate promising computational efficiency and competitive performance, yet struggle with overfitting issues that hinder their scalability. To overcome this challenge, we introduce VideoMAP, a Hybrid Mamba-Transformer framework featuring a novel pre-training approach. VideoMAP uses a 4:1 Mamba-to-Transformer ratio, effectively balancing computational cost and model capacity. This architecture, combined with our proposed frame-wise masked autoregressive pre-training strategy, delivers significant performance gains when scaling to larger models. Additionally, VideoMAP exhibits impressive sample efficiency, significantly outperforming existing methods with less training data. Experiments show that VideoMAP outperforms existing models across various datasets, including Kinetics-400, Something-Something V2, Breakfast, and COIN. Furthermore, we demonstrate the potential of VideoMAP as a visual encoder for multimodal large language models, highlighting its ability to reduce memory usage and enable the processing of longer video sequences. The code is open-source at https://github.com/yunzeliu/MAP