mlsanityData to 7 Oct 2026

AutoRefiner: Improving Autoregressive Video Diffusion Models via Reflective Refinement Over the Stochastic Sampling Path

arXiv 2512.11203 ↗First posted 12 Dec 2025cs.CVcited by 4

On the map: Diffusion models → Video generation

Abstract (arXiv)

Autoregressive video diffusion models (AR-VDMs) show strong promise as scalable alternatives to bidirectional VDMs, enabling real-time and interactive applications. Yet there remains room for improvement in their sample fidelity. A promising solution is inference-time alignment, which optimizes the noise space to improve sample fidelity without updating model parameters. Yet, optimization- or search-based methods are computationally impractical for AR-VDMs. Recent text-to-image (T2I) works address this via feedforward noise refiners that modulate sampled noises in a single forward pass. Can such noise refiners be extended to AR-VDMs? We identify the failure of naively extending T2I noise refiners to AR-VDMs and propose AutoRefiner-a noise refiner tailored for AR-VDMs, with two key designs: pathwise noise refinement and a reflective KV-cache. Experiments demonstrate that AutoRefiner serves as an efficient plug-in for AR-VDMs, effectively enhancing sample fidelity by refining noise along stochastic denoising paths.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 76 of its 87 references that are in the map. First posted on arXiv 12 Dec 2025.

Builds on

76 of 87 references.

Closest ancestors · 25

Same direction, newest first

  1. 2025Self-Forcing++: Towards Minute-Scale High-Quality Video Generation2 Oct
  2. 2025Rolling Forcing: Autoregressive Long Video Diffusion in Real Time29 Sep
  3. 2025StreamDiT: Real-Time Streaming Text-to-Video Generation4 Jul
  4. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion9 Jun
  5. 2025Playing with Transformer at 30+ FPS via Next-Frame Diffusion2 Jun
  6. 2025Long-Context State-Space Video World Models26 May
  7. 2025SkyReels-V2: Infinite-length Film Generative Model17 Apr
  8. 2025ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos20 Mar
  9. 2025AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion10 Mar
  10. 2025Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search31 Jan
  11. 2025Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise14 Jan
  12. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Models10 Dec
13 more
  1. 2024Progressive Autoregressive Video Diffusion Models10 Oct
  2. 2024T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design8 Oct
  3. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer12 Aug
  4. 2024MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence23 Jul
  5. 2024FIFO-Diffusion: Generating Infinite Videos from Text without Training19 May
  6. 2024VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models10 Mar
  7. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models17 Jan
  8. 2023VideoCrafter1: Open Diffusion Models for High-Quality Video Generation30 Oct
  9. 2023Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation27 Sep
  10. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning10 Jul
  11. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generation23 Nov
  12. 2022Imagen Video: High Definition Video Generation with Diffusion Models5 Oct
  13. 2022Video Diffusion Models7 Apr

Other references · 51

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  8. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  9. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  10. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  11. 2022Classifier-Free Diffusion Guidancecited by 5,717
  12. 2022Flow Matching for Generative Modelingcited by 5,426
38 more
  1. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  2. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  3. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  4. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  5. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  6. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  7. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
  8. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  9. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  10. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  11. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  12. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 973
  13. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 950
  14. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 946
  15. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 847
  16. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 634
  17. 2023InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generationcited by 488
  18. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusioncited by 448
  19. 2024InternVideo2: Scaling Foundation Models for Multimodal Video Understandingcited by 310
  20. 2025MAGI-1: Autoregressive Video Generation at Scalecited by 262
  21. 2025LongLive: Real-time Interactive Long Video Generationcited by 237
  22. 2025Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Stepscited by 225
  23. 2016Professor Forcing: A New Algorithm for Training Recurrent Networkscited by 214
  24. 2025History-Guided Video Diffusioncited by 165
  25. 2025WorldMem: Long-term Consistent World Simulation with Memorycited by 152
  26. 2019Generalization in Generation: A closer look at Exposure Biascited by 123
  27. 2024ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimizationcited by 115
  28. 2024Golden Noise for Diffusion Models: A Learning Frameworkcited by 91
  29. 2023Tag2Text: Guiding Vision-Language Model via Image Taggingcited by 84
  30. 2025Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Reviewcited by 82
  31. 2024Large-scale Reinforcement Learning for Diffusion Modelscited by 78
  32. 2024Not All Noises Are Created Equally:Diffusion Noise Selection and Optimizationcited by 70
  33. 2024A Noise is Worth Diffusion Guidancecited by 48
  34. 2025Captain Cinema: Towards Short Movie Generationcited by 48
  35. 2023If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selectioncited by 40
  36. 2025Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Modelscited by 35
  37. 2025How I Warped Your Noise: a Temporally-Correlated Noise Prior for Diffusion Modelscited by 31
  38. 2025Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Modelscited by 23

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Pathwise Test-Time Correction for Autoregressive Long Video Generationcited by 12
  2. 2026Efficient Video Diffusion Models: Advancements and Challengescited by 6
  3. 2026ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Modelscited by 2
  4. 2026Test-Time Noise Guided Adaptation for Realistic Autoregressive Video Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026DSA: Dynamic Step Allocation for Fast Autoregressive Video Generation
  2. 2024Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
  3. 2025Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework
  4. 2026Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation
  5. 2026Test-Time Scaling for Video Diffusion Models via Diagnosis-Guided Candidate Recycling
  6. 2025End-to-End Training for Autoregressive Video Diffusion via Self-Resampling
  7. 2025Adaptive Begin-of-Video Tokens for Autoregressive Video Diffusion Models
  8. 2026In-Context Forcing: Uncovering Context Effects in Autoregressive Video Diffusion