# Streaming Autoregressive Video Generation via Diagonal Distillation

arXiv: https://arxiv.org/abs/2603.09488 · HTML: https://mlsanity.com/paper/2603.09488/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 59 of its 64 references that are in the map.
- First posted on arXiv 10 Mar 2026.

## Placed in

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

## Builds on (most cited first, 30 of 59)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [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)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [Variational Diffusion Models](https://mlsanity.com/paper/2107.00630/) (2021)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [Adversarial Diffusion Distillation](https://mlsanity.com/paper/2311.17042/) (2023)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [Autoregressive Image Generation without Vector Quantization](https://mlsanity.com/paper/2406.11838/) (2024)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [VideoPoet: A Large Language Model for Zero-Shot Video Generation](https://mlsanity.com/paper/2312.14125/) (2023)
- [Phenaki: Variable Length Video Generation From Open Domain Textual Description](https://mlsanity.com/paper/2210.02399/) (2022)
- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models](https://mlsanity.com/paper/2503.09573/) (2025)
- [Generating Videos with Scene Dynamics](https://mlsanity.com/paper/1609.02612/) (2016)
- [Pyramidal Flow Matching for Efficient Video Generative Modeling](https://mlsanity.com/paper/2410.05954/) (2024)

## Built on by (most cited first, 18 of 18)

- [LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation](https://mlsanity.com/paper/2605.18739/) (2026)
- [Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models](https://mlsanity.com/paper/2606.25473/) (2026)
- [One-Forcing: Towards Stable One-Step Autoregressive Video Generation](https://mlsanity.com/paper/2605.23458/) (2026)
- [StreamingEffect: Real-Time Human-Centric Video Effect Generation](https://mlsanity.com/paper/2605.17019/) (2026)
- [Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation](https://mlsanity.com/paper/2603.21864/) (2026)
- [RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO](https://mlsanity.com/paper/2605.15190/) (2026)
- [Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion](https://mlsanity.com/paper/2605.16579/) (2026)
- [From Pixels to States: Rethinking Interactive World Models as Game Engines](https://mlsanity.com/paper/2607.14076/) (2026)
- [Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation](https://mlsanity.com/paper/2605.14382/) (2026)
- [XYZFlow:Scaling Multi dimensional Shortcut Flows for Efficient Generative Modeling](https://mlsanity.com/paper/2608.12276/) (2026)
- [SQuad: Sub-Quadratic Attention Distillation for Efficient Video Generation](https://mlsanity.com/paper/2608.16585/) (2026)
- [ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation](https://mlsanity.com/paper/2609.28923/) (2026)
- [UnStep: Training-Free Acceleration of Causal Video Diffusion with Fewer Steps Than Distillation](https://mlsanity.com/paper/2609.32518/) (2026)
- [In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion](https://mlsanity.com/paper/2609.32540/) (2026)
- [From Scores to Samples: Elastic Forcing for Autoregressive Video Generation](https://mlsanity.com/paper/2609.35491/) (2026)
- [TGuide: Faster Autoregressive Video Diffusion via Historical Trajectory Guidance](https://mlsanity.com/paper/2610.14657/) (2026)
- [LongForcing: Scaling Temporal Manifold Matching for Long-Horizon World Rollout](https://mlsanity.com/paper/2610.18289/) (2026)
- [Glance Forcing: Making Bidirectional Diffusion Autoregressive at a Glance](https://mlsanity.com/paper/2610.20220/) (2026)

## Abstract (arXiv)

Large pretrained diffusion models have significantly enhanced the quality of generated videos, and yet their use in real-time streaming remains limited. Autoregressive models offer a natural framework for sequential frame synthesis but require heavy computation to achieve high fidelity. Diffusion distillation can compress these models into efficient few-step variants, but existing video distillation approaches largely adapt image-specific methods that neglect temporal dependencies. These techniques often excel in image generation but underperform in video synthesis, exhibiting reduced motion coherence, error accumulation over long sequences, and a latency-quality trade-off. We identify two factors that result in these limitations: insufficient utilization of temporal context during step reduction and implicit prediction of subsequent noise levels in next-chunk prediction (i.e., exposure bias). To address these issues, we propose Diagonal Distillation, which operates orthogonally to existing approaches and better exploits temporal information across both video chunks and denoising steps. Central to our approach is an asymmetric generation strategy: more steps early, fewer steps later. This design allows later chunks to inherit rich appearance information from thoroughly processed early chunks, while using partially denoised chunks as conditional inputs for subsequent synthesis. By aligning the implicit prediction of subsequent noise levels during chunk generation with the actual inference conditions, our approach mitigates error propagation and reduces oversaturation in long-range sequences. We further incorporate implicit optical flow modeling to preserve motion quality under strict step constraints. Our method generates a 5-second video in 2.61 seconds (up to 31 FPS), achieving a 277.3x speedup over the undistilled model.