# MarDini: Masked Autoregressive Diffusion for Video Generation at Scale

arXiv: https://arxiv.org/abs/2410.20280 · HTML: https://mlsanity.com/paper/2410.20280/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 94 of its 116 references that are in the map.
- First posted on arXiv 26 Oct 2024.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 94)

- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [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)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)

## Built on by (most cited first, 30 of 49)

- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [Show-o2: Improved Native Unified Multimodal Models](https://mlsanity.com/paper/2506.15564/) (2025)
- [Rolling Forcing: Autoregressive Long Video Diffusion in Real Time](https://mlsanity.com/paper/2509.25161/) (2025)
- [Adaptive Caching for Faster Video Generation with Diffusion Transformers](https://mlsanity.com/paper/2411.02397/) (2024)
- [SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer](https://mlsanity.com/paper/2509.24695/) (2025)
- [SkyReels-A2: Compose Anything in Video Diffusion Transformers](https://mlsanity.com/paper/2504.02436/) (2025)
- [End-to-End Training for Autoregressive Video Diffusion via Self-Resampling](https://mlsanity.com/paper/2512.15702/) (2025)
- [Autoregressive Models in Vision: A Survey](https://mlsanity.com/paper/2411.05902/) (2024)
- [VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention](https://mlsanity.com/paper/2503.15138/) (2025)
- [PAN: A World Model for General, Actionable, and Long-Horizon World Simulation](https://mlsanity.com/paper/2511.09057/) (2025)
- [Geometry-aware 4D Video Generation for Robot Manipulation](https://mlsanity.com/paper/2507.01099/) (2025)
- [Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective](https://mlsanity.com/paper/2507.08801/) (2025)
- [INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling](https://mlsanity.com/paper/2604.07209/) (2026)
- [Towards Precise Scaling Laws for Video Diffusion Transformers](https://mlsanity.com/paper/2411.17470/) (2024)
- [Streaming Autoregressive Video Generation via Diagonal Distillation](https://mlsanity.com/paper/2603.09488/) (2026)
- [Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models](https://mlsanity.com/paper/2507.13162/) (2025)
- [BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2512.12080/) (2025)
- [MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines](https://mlsanity.com/paper/2603.06679/) (2026)
- [Ingredients: Blending Custom Photos with Video Diffusion Transformers](https://mlsanity.com/paper/2501.01790/) (2025)
- [Video Diffusion Transformers are In-Context Learners](https://mlsanity.com/paper/2412.10783/) (2024)
- [Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think](https://mlsanity.com/paper/2503.00948/) (2025)
- [Lance: Unified Multimodal Modeling by Multi-Task Synergy](https://mlsanity.com/paper/2605.18678/) (2026)
- [Can Video Diffusion Model Reconstruct 4D Geometry?](https://mlsanity.com/paper/2503.21082/) (2025)
- [Continuous Visual Autoregressive Generation via Score Maximization](https://mlsanity.com/paper/2505.07812/) (2025)
- [Scaling Zero-Shot Reference-to-Video Generation](https://mlsanity.com/paper/2512.06905/) (2025)
- [ConfRover: Simultaneous Modeling of Protein Conformation and Dynamics via Autoregression](https://mlsanity.com/paper/2505.17478/) (2025)
- [Scaling Sequence-to-Sequence Generative Neural Rendering](https://mlsanity.com/paper/2510.04236/) (2025)
- [AirScape: An Aerial Generative World Model with Motion Controllability](https://mlsanity.com/paper/2507.08885/) (2025)
- [Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion](https://mlsanity.com/paper/2512.23709/) (2025)

## Abstract (arXiv)

We introduce MarDini, a new family of video diffusion models that integrate the advantages of masked auto-regression (MAR) into a unified diffusion model (DM) framework. Here, MAR handles temporal planning, while DM focuses on spatial generation in an asymmetric network design: i) a MAR-based planning model containing most of the parameters generates planning signals for each masked frame using low-resolution input; ii) a lightweight generation model uses these signals to produce high-resolution frames via diffusion de-noising. MarDini's MAR enables video generation conditioned on any number of masked frames at any frame positions: a single model can handle video interpolation (e.g., masking middle frames), image-to-video generation (e.g., masking from the second frame onward), and video expansion (e.g., masking half the frames). The efficient design allocates most of the computational resources to the low-resolution planning model, making computationally expensive but important spatio-temporal attention feasible at scale. MarDini sets a new state-of-the-art for video interpolation; meanwhile, within few inference steps, it efficiently generates videos on par with those of much more expensive advanced image-to-video models.