mlsanityData to 7 Oct 2026

VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory

arXiv 2512.04519 ↗First posted 4 Dec 2025cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

Autoregressive (AR) diffusion enables streaming, interactive long-video generation by producing frames causally, yet maintaining coherence over minute-scale horizons remains challenging due to accumulated errors, motion drift, and content repetition. We approach this problem from a memory perspective, treating video synthesis as a recurrent dynamical process that requires coordinated short- and long-term context. We propose VideoSSM, a Long Video Model that unifies AR diffusion with a hybrid state-space memory. The state-space model (SSM) serves as an evolving global memory of scene dynamics across the entire sequence, while a context window provides local memory for motion cues and fine details. This hybrid design preserves global consistency without frozen, repetitive patterns, supports prompt-adaptive interaction, and scales in linear time with sequence length. Experiments on short- and long-range benchmarks demonstrate state-of-the-art temporal consistency and motion stability among autoregressive video generator especially at minute-scale horizons, enabling content diversity and interactive prompt-based control, thereby establishing a scalable, memory-aware framework for long video generation.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 58 of its 62 references that are in the map. First posted on arXiv 4 Dec 2025.

Builds on

58 of 62 references.

References · 58

  1. 2022Scalable Diffusion Models with Transformerscited by 5,931
  2. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  3. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  4. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  5. 2022Video Diffusion Modelscited by 2,280
  6. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
  7. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,115
  8. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  9. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  10. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  11. 2018Recurrent World Models Facilitate Policy Evolutioncited by 761
  12. 2024Genie: Generative Interactive Environmentscited by 706
38 more
  1. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 651
  2. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 634
  3. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 569
  4. 2024LTX-Video: Realtime Video Latent Diffusioncited by 549
  5. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 523
  6. 2024Gated Delta Networks: Improving Mamba2 with Delta Rulecited by 483
  7. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 479
  8. 2022Phenaki: Variable Length Video Generation From Open Domain Textual Descriptioncited by 475
  9. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Modelscited by 401
  10. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generationcited by 385
  11. 2024Pyramidal Flow Matching for Efficient Video Generative Modelingcited by 354
  12. 2015Deep multi-scale video prediction beyond mean square errorcited by 297
  13. 2025MAGI-1: Autoregressive Video Generation at Scalecited by 262
  14. 2022Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformercited by 244
  15. 2024StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Textcited by 242
  16. 2025LongLive: Real-time Interactive Long Video Generationcited by 237
  17. 2023SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Predictioncited by 231
  18. 2025SkyReels-V2: Infinite-length Film Generative Modelcited by 218
  19. 2025Rolling Forcing: Autoregressive Long Video Diffusion in Real Timecited by 209
  20. 2019Scaling Autoregressive Video Modelscited by 189
  21. 2024Autoregressive Video Generation without Vector Quantizationcited by 180
  22. 2025Self-Forcing++: Towards Minute-Scale High-Quality Video Generationcited by 176
  23. 2023FreeNoise: Tuning-Free Longer Video Diffusion via Noise Reschedulingcited by 173
  24. 2025History-Guided Video Diffusioncited by 165
  25. 2025Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrievalcited by 157
  26. 2025WorldMem: Long-term Consistent World Simulation with Memorycited by 152
  27. 2024VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Modelscited by 124
  28. 2025Video World Models with Long-term Spatial Memorycited by 124
  29. 2025Long-Context Autoregressive Video Modeling with Next-Frame Predictioncited by 119
  30. 2025Long Context Tuning for Video Generationcited by 110
  31. 2025VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memorycited by 102
  32. 2024Loong: Generating Minute-level Long Videos with Autoregressive Language Modelscited by 99
  33. 2025Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generationcited by 93
  34. 2025SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformercited by 91
  35. 2025Mixture of Contexts for Long Video Generationcited by 90
  36. 2025StreamingVLM: Real-Time Understanding for Infinite Video Streamscited by 89
  37. 2024FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attentioncited by 87
  38. 2022NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesiscited by 71

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 37.

39 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 285
  2. 2026LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generationcited by 25
  3. 2026MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokenscited by 20
  4. 2026Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generationcited by 20
  5. 2026OmniRoam: World Wandering via Long-Horizon Panoramic Video Generationcited by 15
  6. 2026Past- and Future-Informed KV Cache Policy with Salience Estimation in Autoregressive Video Diffusioncited by 13
  7. 2026Mode Seeking meets Mean Seeking for Fast Long Video Generationcited by 12
  8. 2026LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generationcited by 12
  9. 2026Addressable Memory for Video World Modelscited by 11
  10. 2025LongVie 2: Multimodal Controllable Ultra-Long Video World Modelcited by 9
  11. 2026Geometry-Aware Implicit Memory for Video World Modelscited by 7
  12. 2026A Mechanistic View on Video Generation as World Models: State and Dynamicscited by 6
27 more
  1. 2026Efficient Video Diffusion Models: Advancements and Challengescited by 6
  2. 2026A2RD: Agentic Autoregressive Diffusion for Long Video Consistencycited by 6
  3. 2026RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPOcited by 6
  4. 2026Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memorycited by 6
  5. 2026Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generationcited by 6
  6. 2026Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithmscited by 5
  7. 2026Head Forcing: Long Autoregressive Video Generation via Head Heterogeneitycited by 5
  8. 2026DySink: Dynamic Frame Sinks for Autoregressive Long Video Generationcited by 5
  9. 2026DIM-WAM: World-Action Modeling with Diverse Historical Event Memorycited by 5
  10. 2026Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillationcited by 5
  11. 2026Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusioncited by 5
  12. 2026Echo-Memory: A Controlled Study of Memory in Action World Modelscited by 4
  13. 2026AlayaWorld: Long-Horizon and Playable Video World Generationcited by 4
  14. 2026From Pixels to States: Rethinking Interactive World Models as Game Enginescited by 4
  15. 2026Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusioncited by 3
  16. 2026VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusioncited by 3
  17. 2026AdaState: Self-Evolving Anchors for Streaming Video Generationcited by 2
  18. 2026OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generationcited by 2
  19. 2026Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generationcited by 2
  20. 2026SlotMem: Character-Addressable Internal Memory for Narrative Long Video Generationcited by 1
  21. 2026WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memorycited by 1
  22. 2026WALL-SS: Scaling Long-horizon World Models via Next-Scale Autoregressioncited by 0
  23. 2026SNF-Bench: Separating Static Drift from Natural Flow in Long-Horizon Fixed-Camera Video Generationcited by 0
  24. 2026UnStep: Training-Free Acceleration of Causal Video Diffusion with Fewer Steps Than Distillationcited by 0
  25. 2026Honeycomb: Constant-Size Scene Memory Representation for Video World Modelscited by 0
  26. 2026DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistencycited by 0
  27. 2026Learning to Retrieve: Internalizing Memory Retrieval for Video World Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026The Past Frames the Future: Memory for Autoregressive Video Generation
  2. 2025Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generation
  3. 2025AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion
  4. 2026UniTemp: Unlocking Video Generation in Any Temporal Order via Bidirectional Distillation
  5. 2026TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL
  6. 2026FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion
  7. 2026SoulX-LiveAct: Towards Hour-Scale Real-Time Human Animation with Neighbor Forcing and ConvKV Memory
  8. 2026Towards Error-Free Long Video Generation