mlsanityData to 7 Oct 2026

Open-Sora 2.0: Training a Commercial-Level Video Generation Model in 200k

arXiv 2503.09642 ↗First posted 12 Mar 2025cs.GR cs.AIcited by 157

Not on the map. Why?

Cited by 57 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Video generation models have achieved remarkable progress in the past year. The quality of AI video continues to improve, but at the cost of larger model size, increased data quantity, and greater demand for training compute. In this report, we present Open-Sora 2.0, a commercial-level video generation model trained for only 200k. With this model, we demonstrate that the cost of training a top-performing video generation model is highly controllable. We detail all techniques that contribute to this efficiency breakthrough, including data curation, model architecture, training strategy, and system optimization. According to human evaluation results and VBench scores, Open-Sora 2.0 is comparable to global leading video generation models including the open-source HunyuanVideo and the closed-source Runway Gen-3 Alpha. By making Open-Sora 2.0 fully open-source, we aim to democratize access to advanced video generation technology, fostering broader innovation and creativity in content creation. All resources are publicly available at: https://github.com/hpcaitech/Open-Sora.

Key facts. Cited by 157 papers in the map (data through 7 Oct 2026). Builds on 30 of its 44 references that are in the map. First posted on arXiv 12 Mar 2025.

Builds on

30 of 44 references.

References · 30

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  4. 2020Scaling Laws for Neural Language Modelscited by 6,411
  5. 2022Classifier-Free Diffusion Guidancecited by 5,717
  6. 2022Flow Matching for Generative Modelingcited by 5,426
  7. 2024Qwen2.5 Technical Reportcited by 4,713
  8. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  9. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  10. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  11. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  12. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,829
18 more
  1. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  2. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  3. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  4. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,278
  5. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 973
  6. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 867
  7. 2024Open-Sora: Democratizing Efficient Video Production for Allcited by 637
  8. 2024Movie Gen: A Cast of Media Foundation Modelscited by 614
  9. 2024Latte: Latent Diffusion Transformer for Video Generationcited by 536
  10. 2023Ring Attention with Blockwise Transformers for Near-Infinite Contextcited by 448
  11. 2025Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Modelscited by 376
  12. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 331
  13. 2024Open-Sora Plan: Open-Source Large Video Generation Modelcited by 286
  14. 2025Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Stepscited by 225
  15. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Modelscited by 209
  16. 2025Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Modelcited by 163
  17. 2021Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Trainingcited by 96
  18. 2025Masked Autoencoders Are Effective Tokenizers for Diffusion Modelscited by 93

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 78; 2026: 79.

157 papers.

Sort:

By area:

  1. 2025VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulnesscited by 289
  2. 2025SkyReels-V2: Infinite-length Film Generative Modelcited by 218
  3. 2025EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Videocited by 191
  4. 2025Self-Forcing++: Towards Minute-Scale High-Quality Video Generationcited by 176
  5. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 137
  6. 2025Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcingcited by 111
  7. 2025SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformercited by 91
  8. 2025OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generationcited by 73
  9. 2025Vid2World: Crafting Video Diffusion Models to Interactive World Modelscited by 67
  10. 2025Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generationcited by 64
  11. 2026WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RLcited by 46
  12. 2026MOVA: Towards Scalable and Synchronized Video-Audio Generationcited by 39
38 more
  1. 2025"PhyWorldBench": A Comprehensive Evaluation of Physical Realism in Text-to-Video Modelscited by 34
  2. 2025Spatia: Video Generation with Updatable Spatial Memorycited by 33
  3. 2026Beyond Language Modeling: An Exploration of Multimodal Pretrainingcited by 32
  4. 2025AToken: A Unified Tokenizer for Visioncited by 30
  5. 2026LoL: Longer than Longer, Scaling Video Generation to Hourcited by 29
  6. 2025Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generationcited by 27
  7. 2025Pack and Force Your Memory: Long-form and Consistent Video Generationcited by 26
  8. 2025Code2Video: A Code-centric Paradigm for Educational Video Generationcited by 23
  9. 2026Flow caching for autoregressive video generationcited by 19
  10. 2025FullDiT2: Efficient In-Context Conditioning for Video Diffusion Transformerscited by 17
  11. 2025World Models That Know When They Don't Know - Controllable Video Generation with Calibrated Uncertaintycited by 16
  12. 2025DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencodercited by 15
  13. 2025Simulating the Visual World with Artificial Intelligence: A Roadmapcited by 15
  14. 2025Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generationcited by 15
  15. 2025DVD-Quant: Data-free Video Diffusion Transformers Quantizationcited by 14
  16. 2026WALL-WM: Carving World Action Modeling at the Event Jointscited by 14
  17. 2026Your One-Stop Solution for AI-Generated Video Detectioncited by 13
  18. 2025ManipDreamer: Boosting Robotic Manipulation World Model with Action Tree and Visual Guidancecited by 11
  19. 2025Video Unlearning via Low-Rank Refusal Vectorcited by 11
  20. 2025Uniform Discrete Diffusion with Metric Path for Video Generationcited by 11
  21. 2025DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generationcited by 11
  22. 2026Lance: Unified Multimodal Modeling by Multi-Task Synergycited by 11
  23. 2026MemoBench: Benchmarking World Modeling in Dynamically Changing Environmentscited by 10
  24. 2025FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edgecited by 9
  25. 2025From Virtual Games to Real-World Playcited by 9
  26. 2025ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraintscited by 9
  27. 2025Recurrent Autoregressive Diffusion: Global Memory Meets Local Attentioncited by 9
  28. 2025How Much 3D Do Video Foundation Models Encode?cited by 9
  29. 2026LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AVcited by 9
  30. 2025FourierFlow: Frequency-aware Flow Matching for Generative Turbulence Modelingcited by 8
  31. 2025Pulp Motion: Framing-aware multimodal camera and human motion generationcited by 8
  32. 2026Olaf-World: Orienting Latent Actions for Video World Modelingcited by 8
  33. 2026Kairos: A Regret-Aware Native World-Action Model Stack for Physical AIcited by 8
  34. 2025DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Spacecited by 7
  35. 2025From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle Velocitycited by 7
  36. 2025RunawayEvil: Jailbreaking the Image-to-Video Generative Modelscited by 7
  37. 2025UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generationcited by 7
  38. 2026OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Modelscited by 7

50 most cited of 157 All 157 (JSON)