mlsanityData to 14 Oct 2026

Long Context Tuning for Video Generation

arXiv 2503.10589 ↗First posted 13 Mar 2025cs.CVcited by 113

On the map: Diffusion models → Video generation

Abstract (arXiv)

Recent advances in video generation can produce realistic, minute-long single-shot videos with scalable diffusion transformers. However, real-world narrative videos require multi-shot scenes with visual and dynamic consistency across shots. In this work, we introduce Long Context Tuning (LCT), a training paradigm that expands the context window of pre-trained single-shot video diffusion models to learn scene-level consistency directly from data. Our method expands full attention mechanisms from individual shots to encompass all shots within a scene, incorporating interleaved 3D position embedding and an asynchronous noise strategy, enabling both joint and auto-regressive shot generation without additional parameters. Models with bidirectional attention after LCT can further be fine-tuned with context-causal attention, facilitating auto-regressive generation with efficient KV-cache. Experiments demonstrate single-shot models after LCT can produce coherent multi-shot scenes and exhibit emerging capabilities, including compositional generation and interactive shot extension, paving the way for more practical visual content creation. See https://guoyww.github.io/projects/long-context-video/ for more details.

Key facts. Cited by 113 papers in the map (data through 14 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 58 of its 80 references that are in the map. First posted on arXiv 13 Mar 2025.

Builds on

58 of 80 references.

Closest ancestors · 30

Same direction, newest first

  1. 2025ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning8 Jan
  2. 2024DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation24 Dec
  3. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer12 Aug
  4. 2024FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention29 Jul
  5. 2024MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence23 Jul
  6. 2024Video-Infinity: Distributed Long Video Generation24 Jun
  7. 2024StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation2 May
  8. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generation2 Apr
  9. 2024StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text21 Mar
  10. 2024Lumiere: A Space-Time Diffusion Model for Video Generation23 Jan
  11. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models17 Jan
  12. 2024VideoStudio: Generating Consistent-Content and Multi-Scene Videos2 Jan
18 more
  1. 2023MEVG: Multi-event Video Generation with Text-to-Video Models7 Dec
  2. 2023VideoBooth: Diffusion-based Video Generation with Image Prompts1 Dec
  3. 2023SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models28 Nov
  4. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets25 Nov
  5. 2023I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models7 Nov
  6. 2023VideoCrafter1: Open Diffusion Models for High-Quality Video Generation30 Oct
  7. 2023FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling23 Oct
  8. 2023DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors18 Oct
  9. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation9 Oct
  10. 2023Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation27 Sep
  11. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning10 Jul
  12. 2023Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising29 May
  13. 2023Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models17 May
  14. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models18 Apr
  15. 2023NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation22 Mar
  16. 2023VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation15 Mar
  17. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generation23 Nov
  18. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Models20 Nov

Other references · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022Scalable Diffusion Models with Transformerscited by 6,054
  3. 2022Flow Matching for Generative Modelingcited by 5,702
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  5. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  6. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  7. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  8. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  9. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  10. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  11. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  12. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,464
16 more
  1. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 681
  2. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 524
  3. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 492
  4. 2022Phenaki: Variable Length Video Generation From Open Domain Textual Descriptioncited by 484
  5. 2022MAGVIT: Masked Generative Video Transformercited by 346
  6. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 301
  7. 2023Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioningcited by 255
  8. 2023Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolutioncited by 229
  9. 2025History-Guided Video Diffusioncited by 171
  10. 2024In-Context LoRA for Diffusion Transformerscited by 158
  11. 2023Make Pixels Dance: High-Dynamic Video Generationcited by 140
  12. 2023Animate-A-Story: Storytelling with Retrieval-Augmented Video Generationcited by 90
  13. 2020A Local-to-Global Approach to Multi-modal Movie Scene Segmentationcited by 60
  14. 2024Mind the Time: Temporally-Controlled Multi-Event Video Generationcited by 40
  15. 2024TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generationcited by 25
  16. 2024Synchronized Video Storytelling: Generating Video Narrations with Structured Storylinecited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 54; 2026: 59.

113 papers.

Sort:

By area:

  1. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 625
  2. 2025LongLive: Real-time Interactive Long Video Generationcited by 265
  3. 2025Seedance 1.0: Exploring the Boundaries of Video Generation Modelscited by 259
  4. 2025Rolling Forcing: Autoregressive Long Video Diffusion in Real Timecited by 234
  5. 2025Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrievalcited by 163
  6. 2025Long-Context Autoregressive Video Modeling with Next-Frame Predictioncited by 123
  7. 2025Mixture of Contexts for Long Video Generationcited by 95
  8. 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generationcited by 90
  9. 2025Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillationcited by 86
  10. 2025Seaweed-7B: Cost-Effective Training of Video Generation Foundation Modelcited by 82
  11. 2025MotionStream: Real-Time Video Generation with Interactive Motion Controlscited by 76
  12. 2026Helios: Real Real-Time Long Video Generation Modelcited by 65
38 more
  1. 2025HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narrativescited by 54
  2. 2025End-to-End Training for Autoregressive Video Diffusion via Self-Resamplingcited by 52
  3. 2025Captain Cinema: Towards Short Movie Generationcited by 48
  4. 2025World-in-World: World Models in a Closed-Loop Worldcited by 47
  5. 2025FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolutioncited by 43
  6. 2025VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memorycited by 42
  7. 2025StoryMem: Multi-shot Long Video Storytelling with Memorycited by 40
  8. 2025MultiShotMaster: A Controllable Multi-Shot Video Generation Frameworkcited by 36
  9. 2025OneStory: Coherent Multi-Shot Video Generation with Adaptive Memorycited by 35
  10. 2025HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Modelscited by 32
  11. 2026Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusioncited by 32
  12. 2025EchoShot: Multi-Shot Portrait Video Generationcited by 29
  13. 2025CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Modelscited by 29
  14. 2026ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytellingcited by 28
  15. 2026VideoMemory: Toward Consistent Video Generation via Memory Integrationcited by 25
  16. 2025MAViS: A Multi-Agent Framework for Long-Sequence Video Storytellingcited by 21
  17. 2025Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generationcited by 21
  18. 2026INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modelingcited by 21
  19. 2025StateSpaceDiffuser: Bringing Long Context to Diffusion World Modelscited by 19
  20. 2025AniMaker: Multi-Agent Animated Storytelling with MCTS-Driven Clip Generationcited by 19
  21. 2025LoViC: Efficient Long Video Generation with Context Compressioncited by 19
  22. 2025FullDiT2: Efficient In-Context Conditioning for Video Diffusion Transformerscited by 18
  23. 2025X-Streamer: Unified Human World Modeling with Audiovisual Interactioncited by 18
  24. 2025MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generationcited by 18
  25. 2025VINCIE: Unlocking In-context Image Editing from Videocited by 17
  26. 2025FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusioncited by 17
  27. 2025WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perceptioncited by 16
  28. 2025BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Modelscited by 16
  29. 2026MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Enginescited by 16
  30. 2026Anchor Forcing: Anchor Memory and Tri-Region RoPE for Interactive Streaming Video Diffusioncited by 16
  31. 2025Cut2Next: Generating Next Shot via In-Context Tuningcited by 15
  32. 2025Video-As-Prompt: Unified Semantic Control for Video Generationcited by 14
  33. 2025ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videoscited by 12
  34. 2025Cross-Frame Representation Alignment for Fine-Tuning Video Diffusion Modelscited by 12
  35. 2026Mode Seeking meets Mean Seeking for Fast Long Video Generationcited by 12
  36. 2025FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusioncited by 10
  37. 2026CubeComposer: Spatio-Temporal Autoregressive 4K 360deg Video Generation from Perspective Videocited by 10
  38. 2026CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narrativescited by 10

50 most cited of 113 All 113 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026CineWeaver: Training-Free Reference-Controllable Multi-Shot Long Video Generation for Cinematic Storytelling
  2. 2024Video Diffusion Transformers are In-Context Learners
  3. 2025MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation
  4. 2025Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
  5. 2026Motion-Adaptive Temporal Attention for Lightweight Video Generation with Stable Diffusion
  6. 2022Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
  7. 2025Temporal In-Context Fine-Tuning with Temporal Reasoning for Versatile Control of Video Diffusion Models
  8. 2023LatentWarp: Consistent Diffusion Latents for Zero-Shot Video-to-Video Translation