mlsanityData to 14 Oct 2026

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation

arXiv 2506.09350 ↗First posted 11 Jun 2025cs.CV cs.AI cs.LGcited by 90

Not on the map. Why?

Cited by 41 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Existing large-scale video generation models are computationally intensive, preventing adoption in real-time and interactive applications. In this work, we propose autoregressive adversarial post-training (AAPT) to transform a pre-trained latent video diffusion model into a real-time, interactive video generator. Our model autoregressively generates a latent frame at a time using a single neural function evaluation (1NFE). The model can stream the result to the user in real time and receive interactive responses as controls to generate the next latent frame. Unlike existing approaches, our method explores adversarial training as an effective paradigm for autoregressive generation. This not only allows us to design an architecture that is more efficient for one-step generation while fully utilizing the KV cache, but also enables training the model in a student-forcing manner that proves to be effective in reducing error accumulation during long video generation. Our experiments demonstrate that our 8B model achieves real-time, 24fps, streaming video generation at 736x416 resolution on a single H100, or 1280x720 on 8xH100 up to a minute long (1440 frames). Visit our research website at https://seaweed-apt.com/2

Key facts. Cited by 90 papers in the map (data through 14 Oct 2026). Builds on 111 of its 124 references that are in the map. First posted on arXiv 11 Jun 2025.

Builds on

111 of 124 references.

References · 111

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  5. 2023GPT-4 Technical Reportcited by 18,396
  6. 2024The Llama 3 Herd of Modelscited by 14,715
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  8. 2022Scalable Diffusion Models with Transformerscited by 6,054
  9. 2022Classifier-Free Diffusion Guidancecited by 5,847
  10. 2022Flow Matching for Generative Modelingcited by 5,702
  11. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  12. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
38 more
  1. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  2. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  4. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,708
  5. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  6. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  7. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  8. 2023Consistency Modelscited by 1,822
  9. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  10. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  11. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,234
  12. 2023One-step Diffusion with Distribution Matching Distillationcited by 1,019
  13. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
  14. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 927
  15. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 881
  16. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  17. 2024Emu3: Next-Token Prediction is All You Needcited by 781
  18. 2023Adversarial Diffusion Distillationcited by 759
  19. 2024Genie: Generative Interactive Environmentscited by 747
  20. 2019Fast Transformer Decoding: One Write-Head is All You Needcited by 717
  21. 2023Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animationcited by 688
  22. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 684
  23. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 681
  24. 2018Which Training Methods for GANs do actually Converge?cited by 679
  25. 2023PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallelcited by 660
  26. 2024Movie Gen: A Cast of Media Foundation Modelscited by 644
  27. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 640
  28. 2023MotionCtrl: A Unified and Flexible Motion Controller for Video Generationcited by 580
  29. 2024FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precisioncited by 519
  30. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 503
  31. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 492
  32. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 460
  33. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 457
  34. 2023Improved Techniques for Training Consistency Modelscited by 439
  35. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 395
  36. 2024Pyramidal Flow Matching for Efficient Video Generative Modelingcited by 366
  37. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 340
  38. 2023Effective Whole-body Pose Estimation with Two-stages Distillationcited by 311

50 most cited of 111 All 111 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 36; 2026: 54.

90 papers.

Sort:

By area:

  1. 2025Rolling Forcing: Autoregressive Long Video Diffusion in Real Timecited by 234
  2. 2025Self-Forcing++: Towards Minute-Scale High-Quality Video Generationcited by 192
  3. 2025Matrix-game 2.0: An open-source real-time and streaming interactive world modelcited by 186
  4. 2026Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generationcited by 184
  5. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 170
  6. 2026Advancing Open-source World Modelscited by 154
  7. 2026DreamDojo: A Generalist Robot World Model from Large-Scale Human Videoscited by 135
  8. 2025RELIC: Interactive Video World Model with Long-Horizon Memorycited by 96
  9. 2025Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistencycited by 86
  10. 2025Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillationcited by 86
  11. 2025Scaling Instruction-Based Video Editing with a High-Quality Synthetic Datasetcited by 79
  12. 2025Dynamic Chunking for End-to-End Hierarchical Sequence Modelingcited by 72
38 more
  1. 2026Context Forcing: Consistent Autoregressive Video Generation with Long Contextcited by 59
  2. 2026Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generationcited by 56
  3. 2025End-to-End Training for Autoregressive Video Diffusion via Self-Resamplingcited by 52
  4. 2025Distribution Matching Distillation Meets Reinforcement Learningcited by 50
  5. 2026Infinite Worlds with Versatile Interactionscited by 48
  6. 2025FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolutioncited by 43
  7. 2025FlashWorld: High-quality 3D Scene Generation within Secondscited by 32
  8. 2026LoL: Longer than Longer, Scaling Video Generation to Hourcited by 32
  9. 2026Transition Matching Distillation for Fast Video Generationcited by 30
  10. 2026LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generationcited by 30
  11. 2025Pack and Force Your Memory: Long-form and Consistent Video Generationcited by 29
  12. 2026AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillationcited by 26
  13. 2025StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatarscited by 25
  14. 2026Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Modelscited by 25
  15. 2025Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervalscited by 24
  16. 2026RealWonder: Real-Time Physical Action-Conditioned Video Generationcited by 22
  17. 2025LoViC: Efficient Long Video Generation with Context Compressioncited by 19
  18. 2025X-Streamer: Unified Human World Modeling with Audiovisual Interactioncited by 18
  19. 2025Simulating the Visual World with Artificial Intelligence: A Roadmapcited by 15
  20. 2026HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoisingcited by 15
  21. 2026One-Forcing: Towards Stable One-Step Autoregressive Video Generationcited by 15
  22. 2026Gamma-World: Generative Multi-Agent World Modeling Beyond Two Playerscited by 15
  23. 2026Code World Model: Coding Agent as World Braincited by 14
  24. 2025X-UniMotion: Animating Human Images with Expressive, Unified and Identity-Agnostic Motion Latentscited by 13
  25. 20253D Scene Prompting for Scene-Consistent Camera-Controllable Video Generationcited by 13
  26. 2026Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generationcited by 13
  27. 2025Adversarial Flow Modelscited by 12
  28. 2026Mode Seeking meets Mean Seeking for Fast Long Video Generationcited by 12
  29. 2026CubeComposer: Spatio-Temporal Autoregressive 4K 360deg Video Generation from Perspective Videocited by 10
  30. 2025Real-Time Motion-Controllable Autoregressive Video Diffusioncited by 9
  31. 2025EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editingcited by 8
  32. 2026S2DiT: Sandwich Diffusion Transformer for Mobile Streaming Video Generationcited by 7
  33. 2026Evolution of Video Generative Foundationscited by 7
  34. 2026Efficient Video Diffusion Models: Advancements and Challengescited by 7
  35. 2025Block Cascading: Training Free Acceleration of Block-Causal Video Modelscited by 6
  36. 2025SemanticGen: Video Generation in Semantic Spacecited by 6
  37. 2026A Mechanistic View on Video Generation as World Models: State and Dynamicscited by 6
  38. 2025Streaming Drag-Oriented Interactive Video Manipulation: Drag Anything, Anytime!cited by 5

50 most cited of 90 All 90 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
  2. 2025Towards One-step Causal Video Generation via Adversarial Self-Distillation
  3. 2025Generative Pre-trained Autoregressive Diffusion Transformer
  4. 2026On-Policy Adversarial Flow Distillation for Autoregressive Video Generation
  5. 2025AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion
  6. 2024Autoregressive Video Generation without Vector Quantization
  7. 2025Playing with Transformer at 30+ FPS via Next-Frame Diffusion
  8. 2025LongLive: Real-time Interactive Long Video Generation