# Mixture of Contexts for Long Video Generation

arXiv: https://arxiv.org/abs/2508.21058 · HTML: https://mlsanity.com/paper/2508.21058/

## Key facts

- Cited by 95 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 66 references that are in the map.
- First posted on arXiv 28 Aug 2025.

## Builds on (most cited first, 30 of 62)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [VideoCrafter1: Open Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2310.19512/) (2023)
- [Lumiere: A Space-Time Diffusion Model for Video Generation](https://mlsanity.com/paper/2401.12945/) (2024)
- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention](https://mlsanity.com/paper/2502.11089/) (2025)
- [OminiControl: Minimal and Universal Control for Diffusion Transformer](https://mlsanity.com/paper/2411.15098/) (2024)
- [Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2309.15818/) (2023)
- [Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models](https://mlsanity.com/paper/2305.10474/) (2023)
- [MAGI-1: Autoregressive Video Generation at Scale](https://mlsanity.com/paper/2505.13211/) (2025)
- [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024)
- [SkyReels-V2: Infinite-length Film Generative Model](https://mlsanity.com/paper/2504.13074/) (2025)
- [Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity](https://mlsanity.com/paper/2502.01776/) (2025)
- [MoBA: Mixture of Block Attention for Long-Context LLMs](https://mlsanity.com/paper/2502.13189/) (2025)
- [NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation](https://mlsanity.com/paper/2303.12346/) (2023)

## Built on by (most cited first, 30 of 95)

- [Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory](https://mlsanity.com/paper/2604.08995/) (2026)
- [Stable Video Infinity: Infinite-Length Video Generation with Error Recycling](https://mlsanity.com/paper/2510.09212/) (2025)
- [Helios: Real Real-Time Long Video Generation Model](https://mlsanity.com/paper/2603.04379/) (2026)
- [HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives](https://mlsanity.com/paper/2510.20822/) (2025)
- [End-to-End Training for Autoregressive Video Diffusion via Self-Resampling](https://mlsanity.com/paper/2512.15702/) (2025)
- [World-in-World: World Models in a Closed-Loop World](https://mlsanity.com/paper/2510.18135/) (2025)
- [MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives](https://mlsanity.com/paper/2512.14699/) (2025)
- [VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory](https://mlsanity.com/paper/2512.04519/) (2025)
- [StoryMem: Multi-shot Long Video Storytelling with Memory](https://mlsanity.com/paper/2512.19539/) (2025)
- [MultiShotMaster: A Controllable Multi-Shot Video Generation Framework](https://mlsanity.com/paper/2512.03041/) (2025)
- [OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory](https://mlsanity.com/paper/2512.07802/) (2025)
- [Pack and Force Your Memory: Long-form and Consistent Video Generation](https://mlsanity.com/paper/2510.01784/) (2025)
- [ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling](https://mlsanity.com/paper/2603.25746/) (2026)
- [SLA2: Sparse-Linear Attention with Learnable Routing and QAT](https://mlsanity.com/paper/2602.12675/) (2026)
- [Bidirectional Sparse Attention for Faster Video Diffusion Training](https://mlsanity.com/paper/2509.01085/) (2025)
- [X-Streamer: Unified Human World Modeling with Audiovisual Interaction](https://mlsanity.com/paper/2509.21574/) (2025)
- [MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generation](https://mlsanity.com/paper/2510.18692/) (2025)
- [SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning](https://mlsanity.com/paper/2602.13515/) (2026)
- [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)
- [Anchor Forcing: Anchor Memory and Tri-Region RoPE for Interactive Streaming Video Diffusion](https://mlsanity.com/paper/2603.13405/) (2026)
- [Pathwise Test-Time Correction for Autoregressive Long Video Generation](https://mlsanity.com/paper/2602.05871/) (2026)
- [Addressable Memory for Video World Models](https://mlsanity.com/paper/2608.07408/) (2026)
- [Alaya-EVOKE: From Linear-Scaling Supervision to Endless World](https://mlsanity.com/paper/2608.13546/) (2026)
- [Geometry-Aware Implicit Memory for Video World Models](https://mlsanity.com/paper/2606.02436/) (2026)
- [Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention](https://mlsanity.com/paper/2602.04789/) (2026)
- [Mode Seeking meets Mean Seeking for Fast Long Video Generation](https://mlsanity.com/paper/2602.24289/) (2026)
- [Speed3R: Sparse Feed-forward 3D Reconstruction Models](https://mlsanity.com/paper/2603.08055/) (2026)
- [SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing](https://mlsanity.com/paper/2603.08982/) (2026)
- [CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives](https://mlsanity.com/paper/2605.12496/) (2026)

## Abstract (arXiv)

Long video generation is fundamentally a long context memory problem: models must retain and retrieve salient events across a long range without collapsing or drifting. However, scaling diffusion transformers to generate long-context videos is fundamentally limited by the quadratic cost of self-attention, which makes memory and computation intractable and difficult to optimize for long sequences. We recast long-context video generation as an internal information retrieval task and propose a simple, learnable sparse attention routing module, Mixture of Contexts (MoC), as an effective long-term memory retrieval engine. In MoC, each query dynamically selects a few informative chunks plus mandatory anchors (caption, local windows) to attend to, with causal routing that prevents loop closures. As we scale the data and gradually sparsify the routing, the model allocates compute to salient history, preserving identities, actions, and scenes over minutes of content. Efficiency follows as a byproduct of retrieval (near-linear scaling), which enables practical training and synthesis, and the emergence of memory and consistency at the scale of minutes.