mlsanityData to 14 Oct 2026

History-Guided Video Diffusion

arXiv 2502.06764 ↗First posted 10 Feb 2025cs.LG cs.CVcited by 171

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Classifier-free guidance (CFG) is a key technique for improving conditional generation in diffusion models, enabling more accurate control while enhancing sample quality. It is natural to extend this technique to video diffusion, which generates video conditioned on a variable number of context frames, collectively referred to as history. However, we find two key challenges to guiding with variable-length history: architectures that only support fixed-size conditioning, and the empirical observation that CFG-style history dropout performs poorly. To address this, we propose the Diffusion Forcing Transformer (DFoT), a video diffusion architecture and theoretically grounded training objective that jointly enable conditioning on a flexible number of history frames. We then introduce History Guidance, a family of guidance methods uniquely enabled by DFoT. We show that its simplest form, vanilla history guidance, already significantly improves video generation quality and temporal consistency. A more advanced method, history guidance across time and frequency further enhances motion dynamics, enables compositional generalization to out-of-distribution history, and can stably roll out extremely long videos. Project website: https://boyuan.space/history-guidance

Key facts. Cited by 171 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 56 of its 71 references that are in the map. First posted on arXiv 10 Feb 2025.

Builds on

56 of 71 references.

Closest ancestors · 18

Same direction, newest first

  1. 2024Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion25 Oct
  2. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion1 Jul
  3. 2024Tutorial on Diffusion Models for Imaging and Vision26 Mar
  4. 2023Analyzing and Improving the Training Dynamics of Diffusion Models5 Dec
  5. 2023Common Diffusion Noise Schedules and Sample Steps are Flawed15 May
  6. 2023Efficient Diffusion Training via Min-SNR Weighting Strategy16 Mar
  7. 2023Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC22 Feb
  8. 2023Simple diffusion: End-to-end diffusion for high resolution images26 Jan
  9. 2023On the Importance of Noise Scheduling for Diffusion Models26 Jan
  10. 2022Scalable Diffusion Models with Transformers19 Dec
  11. 2022All are Worth Words: A ViT Backbone for Diffusion Models25 Sep
  12. 2022Classifier-Free Diffusion Guidance26 Jul
6 more
  1. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  2. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  3. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  5. 2020Denoising Diffusion Implicit Models6 Oct
  6. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 38

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  5. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  6. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  7. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  8. 2022Video Diffusion Modelscited by 2,305
  9. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  10. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,186
  11. 2017The Kinetics Human Action Video Datasetcited by 1,909
  12. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
26 more
  1. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,778
  2. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  3. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  4. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,476
  5. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,433
  6. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,234
  7. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 881
  8. 2023ModelScope Text-to-Video Technical Reportcited by 658
  9. 2024Open-Sora: Democratizing Efficient Video Production for Allcited by 652
  10. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 640
  11. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 624
  12. 2024Latte: Latent Diffusion Transformer for Video Generationcited by 546
  13. 2023DynamiCrafter: Animating Open-domain Images with Video Diffusion Priorscited by 471
  14. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 432
  15. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generationcited by 388
  16. 2024Pyramidal Flow Matching for Efficient Video Generative Modelingcited by 366
  17. 2022MAGVIT: Masked Generative Video Transformercited by 346
  18. 2023Photorealistic Video Generation with Diffusion Modelscited by 306
  19. 2022Novel View Synthesis with Diffusion Modelscited by 300
  20. 2024Open-Sora Plan: Open-Source Large Video Generation Modelcited by 296
  21. 2023Diffusion-based Generation, Optimization, and Planning in 3D Scenescited by 239
  22. 2023Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulationcited by 138
  23. 2024Rolling Diffusion Modelscited by 104
  24. 2024Controlling Space and Time with Diffusion Modelscited by 66
  25. 2022Temporally Consistent Transformers for Video Generationcited by 44
  26. 2024Compositional Generative Modeling: A Single Model is Not All You Needcited by 41

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 65; 2026: 106.

171 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. 2026Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generationcited by 184
  4. 2025WorldMem: Long-term Consistent World Simulation with Memorycited by 168
  5. 2025Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrievalcited by 163
  6. 2025Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Modelscited by 143
  7. 2025Video World Models with Long-term Spatial Memorycited by 136
  8. 2025Test-Time Training Done Rightcited by 130
  9. 2025Long Context Tuning for Video Generationcited by 113
  10. 2025Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modelingcited by 96
  11. 2025RELIC: Interactive Video World Model with Long-Horizon Memorycited by 96
  12. 2025Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillationcited by 86
38 more
  1. 2025Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compressioncited by 85
  2. 2025Stable Video Infinity: Infinite-Length Video Generation with Error Recyclingcited by 73
  3. 2025Large Video Planner Enables Generalizable Robot Controlcited by 70
  4. 2026Helios: Real Real-Time Long Video Generation Modelcited by 65
  5. 2025Long-Context State-Space Video World Modelscited by 64
  6. 2025Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraftcited by 52
  7. 2025End-to-End Training for Autoregressive Video Diffusion via Self-Resamplingcited by 52
  8. 2025MindJourney: Test-Time Scaling with World Models for Spatial Reasoningcited by 50
  9. 2025VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memorycited by 42
  10. 2025Spatia: Video Generation with Updatable Spatial Memorycited by 40
  11. 2025OneStory: Coherent Multi-Shot Video Generation with Adaptive Memorycited by 35
  12. 2025Astra: General Interactive World Model with Autoregressive Denoisingcited by 33
  13. 2025HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Modelscited by 32
  14. 2026Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusioncited by 32
  15. 2026Interactive World Simulator for Robot Policy Training and Evaluationcited by 31
  16. 2026LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Modelscited by 28
  17. 2026Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Modelscited by 26
  18. 2026AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillationcited by 26
  19. 2026Flow caching for autoregressive video generationcited by 25
  20. 2026Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generationcited by 24
  21. 2025A Survey of Interactive Generative Videocited by 23
  22. 2025Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspectivecited by 22
  23. 2025Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generationcited by 21
  24. 2025EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memorycited by 20
  25. 2025StateSpaceDiffuser: Bringing Long Context to Diffusion World Modelscited by 19
  26. 2026Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversationcited by 19
  27. 2025X-Streamer: Unified Human World Modeling with Audiovisual Interactioncited by 18
  28. 2026WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memoriescited by 18
  29. 2026MBench: A Comprehensive Benchmark on Memory Capability for Video World Modelscited by 18
  30. 2025ORV: 4D Occupancy-centric Robot Video Generationcited by 17
  31. 2025Generative Pre-trained Autoregressive Diffusion Transformercited by 16
  32. 2025WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perceptioncited by 16
  33. 2025BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Modelscited by 16
  34. 2026LIVE: Long-horizon Interactive Video World Modelingcited by 16
  35. 2026MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Enginescited by 16
  36. 2026Anchor Forcing: Anchor Memory and Tri-Region RoPE for Interactive Streaming Video Diffusioncited by 16
  37. 2025Yan: Foundational Interactive Video Generationcited by 15
  38. 2025True Self-Supervised Novel View Synthesis is Transferablecited by 15

50 most cited of 171 All 171 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Dynamic Classifier-Free Diffusion Guidance via Online Feedback
  2. 2025Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models
  3. 2026Self-Aligned Forcing: Streaming Video Diffusion with Differentiable Noisy History
  4. 2025Temporal In-Context Fine-Tuning with Temporal Reasoning for Versatile Control of Video Diffusion Models
  5. 2024Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling
  6. 2025Feedback Guidance of Diffusion Models
  7. 2025Learn to Guide Your Diffusion Model
  8. 2026Learned End-to-End Guidance Schedules for Diffusion Models