mlsanityData to 7 Oct 2026

Video generation

1,316 papers6 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: video, motion, generation, video generation, diffusion

Key facts. Video generation: 1,316 papers on arXiv since 2022 (data through 7 Oct 2026). 467 of its 1,316 mapped papers (35%) cite “CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer” (2024, arXiv 2408.06072). 452 of its 1,316 mapped papers (34%) cite “Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets” (2023, arXiv 2311.15127). 58 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

58 new papers, 17 Sep – 7 Oct; 6 this week.

  1. This week · 6
  2. GRACE: Generation-aware latent compression for efficient video generation
  3. MORCA: Offline-to-Online Reinforcement Learning for Adaptive Cache Reuse in Video Diffusion Acceleration
  4. Backend-Agnostic Sparse Attention for Fast High-Resolution Visual Generation
  5. S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation
  6. MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
  7. Level-of-Token Diffusion also fits: 3D, point cloud and scene generation
  8. Earlier · 52
  9. CleanMDM: Clean Motion Diffusion Model for Multimodal Motion Cleanup
  10. PixReenact: Pixel-Conditioned Causal Video Diffusion for Streaming Head-Avatar Reenactment
  11. SUAVE: Unified Video-Action Models via Masked Diffusion
  12. FADE: Frame-Aware Diffusion-Transformer-based Multi-Concept Erasure for Video Unlearning
All 58
  1. VDOT++: Unified Few-Step Video Generation via Unbalanced Optimal Transport Distillation
  2. Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation
  3. Does Physics Live in the Activations? Localizing Physical Quantities in Video Diffusion Models
  4. In-Distribution Forcing for Long Video Generation at Test Time
  5. Parasitic Co-Denoising: Unlocking 3D Human Motion Generation in a Frozen Video Diffusion Model
  6. SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation
  7. Dream4ACT: A Shared Visual Action Interface for Multi-Embodiment Video-Action Modeling
  8. PartiCam: Camera Controlled Video Generation with Reward Guidance
  9. DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency
  10. PARK: Accurate Block Retrieval for Sparse Attention in Video Diffusion Transformers
  11. Future Video Generation Better Aligns with the Human Visual Cortex than Observed Video
  12. In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion also fits: Diffusion foundations and sampling
  13. LongLive-Plug: Once-for-All Distillation for Video Generation
  14. Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE
  15. Self-Aligned Forcing: Streaming Video Diffusion with Differentiable Noisy History
  16. Rollout-Marginal Distillation for Long-Horizon Autoregressive Video Generation
  17. ReCaVSR: One-Step Streaming Diffusion Video Super-Resolution with Recycled Latents and Learned Cache Routing also fits: Inverse problems and image restoration
  18. DIET: Deletion-response Expert Trimming for Video Diffusion Transformers also fits: Robustness, privacy and adversarial aspects
  19. Parameterized Stripe Attention for Efficient Video Generation
  20. Motion Concept Unlearning in Video Diffusion Models
  21. Learning via Self-Consistency for Diffusion-based Video Reasoning
  22. FastVR: Efficient Streaming Video Restoration with One-Step Diffusion also fits: Inverse problems and image restoration
  23. PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformers also fits: Inverse problems and image restoration
  24. Temporal-Attention Head Specialization During Video Diffusion Training
  25. CoRe: Co-Evolving Reward Models for Mitigating Latent Reward Hacking in Video Diffusion Models
  26. Lagrangian--Hamiltonian Flows for Video Prediction and Image Generation: A Symplectic Perspective also fits: Flow matching, time series and science
  27. BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusion
  28. Sol-H3: Recursive Self-Improvement for MiniMax-H3 Inference Acceleration on Sol-Engine across Cloud and Edge also fits: Diffusion foundations and sampling
  29. From Static to Dynamic: On-Policy Distillation from Image to Video Diffusion Models
  30. MotionSpaceFlow: Representation-Aware Flow Matching in Direct Motion Space
  31. DraftAttention2: Fast Video Diffusion with Low-Resolution-Guided Mixed-Precision Attention
  32. UnStep: Training-Free Acceleration of Causal Video Diffusion with Fewer Steps Than Distillation
  33. Carnator: Fast Text-to-Video Generation with Generation-Native Compatibility-Guided Cross-Request Reuse
  34. OneFixer: High-Quality and Consistent One-Step Autoregressive 3DGS Refinement for Driving Scenes also fits: 3D, point cloud and scene generation
  35. DyMD: Preserving Interaction Dynamics through Distribution Matching Distillation in Few-Step Video World Models
  36. Where Compute Matters: Heterogeneous Attention for Efficient Video Diffusion
  37. Timo: Taming Multimodal Diffusion Transformer for Human Motion Generation
  38. ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation
  39. Latent evolving World Action Model also fits: Diffusion and flow policies for robotics
  40. Streaming Video Editing with Easy Adaptation
  41. Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms
  42. SparkDiffusion: Mitigating the High-Sparsity Trap --- A Unified Framework for up to 265× Single-GPU Acceleration of Visual Generation
  43. MT-WAM: Reorienting the One-Pass Predictive Representation Toward Action Generation
  44. CompAdapt: Adaptable Composite Motion Modeling for Physics-Consistent Text-to-Video Generation
  45. JEPA Guided Diffusion: Predictive Vision-Language Conditioning for Generative Traffic Forecasting also fits: Diffusion and flow policies for robotics
  46. Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
  47. DART: Distillation-Aware Reparameterization for Training-Free LoRA Reuse in Few-Step Video Diffusion Models
  48. PACE: Precise AI Cinematic Expression also fits: 3D, point cloud and scene generation

Foundations

Most cited by papers here

  1. CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer2024cited by 467 here
  2. Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets2023cited by 452 here
  3. Video Diffusion Models2022cited by 376 here
  4. Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models2023cited by 374 here
  5. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning2023cited by 355 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2020Denoising Diffusion Probabilistic Modelscited by 765 here
  2. 2020Denoising Diffusion Implicit Modelscited by 516 here
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 275 here
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 670 here
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 258 here
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 280 here
  7. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 349 here
  8. 2022Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generationcited by 285 here
  9. 2023Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generatorscited by 211 here
  10. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 355 here
  11. 2023VideoCrafter1: Open Diffusion Models for High-Quality Video Generationcited by 173 here
  12. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Modelscited by 173 here
12 more it builds on, not in this chain
  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 294 here
  2. 2022Video Diffusion Modelscited by 376 here
  3. 2022Classifier-Free Diffusion Guidancecited by 295 here
  4. 2022Flow Matching for Generative Modelingcited by 183 here
  5. 2022Scalable Diffusion Models with Transformerscited by 463 here
  6. 2023Structure and Content-Guided Video Synthesis with Diffusion Modelscited by 191 here
  7. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 307 here
  8. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 374 here
  9. 2023ModelScope Text-to-Video Technical Reportcited by 219 here
  10. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 452 here
  11. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 205 here
  12. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 467 here

The 24 most cited of 2,832.

Browse

30 of 1,316, ranked 6–35

  1. 6Imagen Video: High Definition Video Generation with Diffusion Models2022349
  2. 7Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation2022285
  3. 8ModelScope Text-to-Video Technical Report2023219
  4. 9Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators2023211
  5. 10Structure and Content-Guided Video Synthesis with Diffusion Models2023191
  6. 11VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models2024173
  7. 12VideoCrafter1: Open Diffusion Models for High-Quality Video Generation2023173
  8. 13MagicVideo: Efficient Video Generation With Latent Diffusion Models2022172
  9. 14Latte: Latent Diffusion Transformer for Video Generation2024160
  10. 15FateZero: Fusing Attentions for Zero-shot Text-based Video Editing2023157
All 30
  1. 16Human Motion Diffusion Model2022141
  2. 17Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion2025139
  3. 18LTX-Video: Realtime Video Latent Diffusion2024137
  4. 19MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model2022132
  5. 20LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models2023129
  6. 21From Slow Bidirectional to Fast Autoregressive Video Diffusion Models2024126
  7. 22Latent Video Diffusion Models for High-Fidelity Long Video Generation2022126
  8. 23Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models2023124
  9. 24DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors2023117
  10. 25I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models2023117
  11. 26VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation2023114
  12. 27Pix2Video: Video Editing using Image Diffusion2023107
  13. 28Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation2023105
  14. 29Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity2025104
  15. 30ControlVideo: Training-free Controllable Text-to-Video Generation2023103
  16. 31Executing your Commands via Motion Diffusion in Latent Space202299
  17. 32Pyramidal Flow Matching for Efficient Video Generative Modeling202495
  18. 33Lumiere: A Space-Time Diffusion Model for Video Generation202493
  19. 34Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation202392
  20. 35MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation202290