# An Empirical Study of Autoregressive Pre-training from Videos

arXiv: https://arxiv.org/abs/2501.05453 · HTML: https://mlsanity.com/paper/2501.05453/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 66 references that are in the map.
- First posted on arXiv 9 Jan 2025.

## Builds on (most cited first, 30 of 54)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)

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

- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning](https://mlsanity.com/paper/2603.14482/) (2026)
- [Scaling Laws for Optimal Data Mixtures](https://mlsanity.com/paper/2507.09404/) (2025)
- [Scaling Laws for Native Multimodal Models](https://mlsanity.com/paper/2504.07951/) (2025)
- [VaViM and VaVAM: Autonomous Driving through Video Generative Modeling](https://mlsanity.com/paper/2502.15672/) (2025)
- [Past- and Future-Informed KV Cache Policy with Salience Estimation in Autoregressive Video Diffusion](https://mlsanity.com/paper/2601.21896/) (2026)
- [Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening](https://mlsanity.com/paper/2509.08502/) (2025)
- [Learning Streaming Video Representation via Multitask Training](https://mlsanity.com/paper/2504.20041/) (2025)
- [Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing](https://mlsanity.com/paper/2603.12254/) (2026)
- [VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization](https://mlsanity.com/paper/2604.12887/) (2026)
- [Frozen Forecasting: A Unified Evaluation](https://mlsanity.com/paper/2507.13942/) (2025)
- [Uncovering the Latent Potential of Deep Intermediate Representations](https://mlsanity.com/paper/2605.23033/) (2026)
- [Poly-Autoregressive Prediction for Modeling Interactions](https://mlsanity.com/paper/2502.08646/) (2025)
- [AutoCas: Autoregressive Cascade Predictor in Social Networks via Large Language Models](https://mlsanity.com/paper/2502.18040/) (2025)
- [Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations](https://mlsanity.com/paper/2512.21004/) (2025)
- [Tracking by Predicting 3-D Gaussians Over Time](https://mlsanity.com/paper/2512.22489/) (2025)
- [Separators in Enhancing Autoregressive Pretraining for Vision Mamba](https://mlsanity.com/paper/2603.03806/) (2026)
- [What Cohort INRs Encode and Where to Freeze Them](https://mlsanity.com/paper/2605.08298/) (2026)
- [TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining](https://mlsanity.com/paper/2609.33419/) (2026)

## Abstract (arXiv)

We empirically study autoregressive pre-training from videos. To perform our study, we construct a series of autoregressive video models, called Toto. We treat videos as sequences of visual tokens and train transformer models to autoregressively predict future tokens. Our models are pre-trained on a diverse dataset of videos and images comprising over 1 trillion visual tokens. We explore different architectural, training, and inference design choices. We evaluate the learned visual representations on a range of downstream tasks including image recognition, video classification, object tracking, and robotics. Our results demonstrate that, despite minimal inductive biases, autoregressive pre-training leads to competitive performance across all benchmarks. Finally, we find that scaling our video models results in similar scaling curves to those seen in language models, albeit with a different rate. More details at https://brjathu.github.io/toto/