mlsanityData to 14 Oct 2026

RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers

arXiv 2502.15894 ↗First posted 21 Feb 2025cs.CVcited by 66

On the map: Diffusion models → Video generation

Abstract (arXiv)

Recent advancements in video generation have enabled models to synthesize high-quality, minute-long videos. However, generating even longer videos with temporal coherence remains a major challenge and existing length extrapolation methods lead to temporal repetition or motion deceleration. In this work, we systematically analyze the role of frequency components in positional embeddings and identify an intrinsic frequency that primarily governs extrapolation behavior. Based on this insight, we propose RIFLEx, a minimal yet effective approach that reduces the intrinsic frequency to suppress repetition while preserving motion consistency, without requiring any additional modifications. RIFLEx offers a true free lunch--achieving high-quality 2x extrapolation on state-of-the-art video diffusion transformers in a completely training-free manner. Moreover, it enhances quality and enables 3x extrapolation by minimal fine-tuning without long videos. Project page and codes: https://riflex-video.github.io/.

Key facts. Cited by 66 papers in the map (data through 14 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 52 of its 57 references that are in the map. First posted on arXiv 21 Feb 2025.

Builds on

52 of 57 references.

Closest ancestors · 15

Same direction, newest first

  1. 2025Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion15 Jan
  2. 2024LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity13 Dec
  3. 2024Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation2 Dec
  4. 2024ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation27 Oct
  5. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer12 Aug
  6. 2024FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention29 Jul
  7. 2024Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model22 Jun
  8. 2024FIFO-Diffusion: Generating Infinite Videos from Text without Training19 May
  9. 2024Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models7 May
  10. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets25 Nov
  11. 2023FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling23 Oct
  12. 2023DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors18 Oct
3 more
  1. 2023Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising29 May
  2. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generation23 Nov
  3. 2022Imagen Video: High Definition Video Generation with Diffusion Models5 Oct

Other references · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2022Scalable Diffusion Models with Transformerscited by 6,054
  7. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  8. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  9. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  10. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  11. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,103
  12. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 985
25 more
  1. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 881
  2. 2025Cosmos World Foundation Model Platform for Physical AIcited by 864
  3. 2024Emu3: Next-Token Prediction is All You Needcited by 781
  4. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 740
  5. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 658
  6. 2024Open-Sora: Democratizing Efficient Video Production for Allcited by 652
  7. 2023YaRN: Efficient Context Window Extension of Large Language Modelscited by 601
  8. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 502
  9. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 492
  10. 2023Generative Multimodal Models are In-Context Learnerscited by 446
  11. 2024LongRoPE: Extending LLM Context Window Beyond 2 Million Tokenscited by 313
  12. 2024Open-Sora Plan: Open-Source Large Video Generation Modelcited by 296
  13. 2024VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generationcited by 295
  14. 2021GODIVA: Generating Open-DomaIn Videos from nAtural Descriptionscited by 256
  15. 2021N"UWA: Visual Synthesis Pre-training for Neural visUal World creAtioncited by 253
  16. 2022Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformercited by 244
  17. 2022EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equationscited by 172
  18. 2024SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Accelerationcited by 160
  19. 2023VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planningcited by 141
  20. 2024Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiTcited by 132
  21. 2024SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantizationcited by 114
  22. 2024Loong: Generating Minute-level Long Videos with Autoregressive Language Modelscited by 99
  23. 2024FiT: Flexible Vision Transformer for Diffusion Modelcited by 85
  24. 2022NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesiscited by 71
  25. 2024Allegro: Open the Black Box of Commercial-Level Video Generation Modelcited by 70

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 33; 2026: 33.

66 papers.

Sort:

By area:

  1. 2025LongLive: Real-time Interactive Long Video Generationcited by 265
  2. 2025Self-Forcing++: Towards Minute-Scale High-Quality Video Generationcited by 192
  3. 2026Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generationcited by 184
  4. 2025Long-Context Autoregressive Video Modeling with Next-Frame Predictioncited by 123
  5. 2025SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inferencecited by 120
  6. 2025Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutationcited by 106
  7. 2025Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillationcited by 86
  8. 2025Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generationcited by 69
  9. 2025DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learningcited by 65
  10. 2026Context Forcing: Consistent Autoregressive Video Generation with Long Contextcited by 59
  11. 2026Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generationcited by 56
  12. 2025VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memorycited by 42
38 more
  1. 2025FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesiscited by 37
  2. 2026LoL: Longer than Longer, Scaling Video Generation to Hourcited by 32
  3. 2025Concat-ID: Towards Universal Identity-Preserving Video Synthesiscited by 28
  4. 2026MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokenscited by 27
  5. 2026VideoMemory: Toward Consistent Video Generation via Memory Integrationcited by 25
  6. 2026Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generationcited by 24
  7. 2026Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantizationcited by 23
  8. 2025NarrLV: Towards a Comprehensive Narrative-Centric Evaluation for Long Video Generationcited by 22
  9. 2025LongVie: Multimodal-Guided Controllable Ultra-Long Video Generationcited by 22
  10. 2025LoViC: Efficient Long Video Generation with Context Compressioncited by 19
  11. 2025FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusioncited by 17
  12. 2025Think Before You Diffuse: Infusing Physical Rules into Video Diffusioncited by 16
  13. 2026LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generationcited by 16
  14. 2026Addressable Memory for Video World Modelscited by 15
  15. 2025DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusioncited by 14
  16. 2025ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videoscited by 12
  17. 2025UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformerscited by 12
  18. 2025UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformerscited by 12
  19. 2026Mode Seeking meets Mean Seeking for Fast Long Video Generationcited by 12
  20. 2025LongDWM: Cross-Granularity Distillation for Building a Long-Term Driving World Modelcited by 9
  21. 2025BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generationcited by 9
  22. 2026Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generationcited by 9
  23. 2025VideoCoF: Unified Video Editing with Temporal Reasonercited by 8
  24. 2026Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generationcited by 7
  25. 2025Scaling Diffusion Transformers Efficiently via μPcited by 6
  26. 2025FreeViS: Training-free Video Stylization with Inconsistent Referencescited by 6
  27. 2026Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesiscited by 6
  28. 2026Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithmscited by 5
  29. 2025Pusa V1.0: Unlocking Temporal Control in Pretrained Video Diffusion Models via Vectorized Timestep Adaptationcited by 4
  30. 2025View-Consistent Diffusion Representations for 3D-Consistent Video Generationcited by 4
  31. 2025LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encodingcited by 3
  32. 2025FastInit: Fast Noise Initialization for Temporally Consistent Video Generationcited by 3
  33. 2025Let Your Video Listen to Your Music!cited by 3
  34. 2026Free-Lunch Long Video Generation via Layer-Adaptive O.O.D Correctioncited by 3
  35. 2026SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformerscited by 3
  36. 2026LVSA: Training-Free Sparse Attention for Long Video Diffusioncited by 3
  37. 2025Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformercited by 2
  38. 2026FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstructioncited by 2

50 most cited of 66 All 66 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024LTX-Video: Realtime Video Latent Diffusion
  2. 2026Steering Video Diffusion Transformers with Massive Activations
  3. 2026Train Short, Inference Long: Training-free Horizon Extension for Autoregressive Video Generation
  4. 2024Video Motion Transfer with Diffusion Transformers
  5. 2026ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer
  6. 2025MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation
  7. 2026TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion
  8. 2025EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation