mlsanityData to 7 Oct 2026

Seedance 2.0: Advancing Video Generation for World Complexity

arXiv 2604.14148 ↗First posted 15 Apr 2026cs.CVcited by 142

Not on the map. Why?

Cited by 26 in World models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Seedance 2.0 is a new native multi-modal audio-video generation model, officially released in China in early February 2026. Compared with its predecessors, Seedance 1.0 and 1.5 Pro, Seedance 2.0 adopts a unified, highly efficient, and large-scale architecture for multi-modal audio-video joint generation. This allows it to support four input modalities: text, image, audio, and video, by integrating one of the most comprehensive suites of multi-modal content reference and editing capabilities available in the industry to date. It delivers substantial, well-rounded improvements across all key sub-dimensions of video and audio generation. In both expert evaluations and public user tests, the model has demonstrated performance on par with the leading levels in the field. Seedance 2.0 supports direct generation of audio-video content with durations ranging from 4 to 15 seconds, with native output resolutions of 480p and 720p. For multi-modal inputs as reference, its current open platform supports up to 3 video clips, 9 images, and 3 audio clips. In addition, we provide Seedance 2.0 Fast version, an accelerated variant of Seedance 2.0 designed to boost generation speed for low-latency scenarios. Seedance 2.0 has delivered significant improvements to its foundational generation capabilities and multi-modal generation performance, bringing an enhanced creative experience for end users.

Key facts. Cited by 142 papers in the map (data through 7 Oct 2026). Builds on 14 of its 19 references that are in the map. First posted on arXiv 15 Apr 2026.

Builds on

14 of 19 references.

References · 14

  1. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  2. 2025DanceGRPO: Unleashing GRPO on Visual Generationcited by 388
  3. 2025Seed1.5-VL Technical Reportcited by 367
  4. 2025Seedance 1.0: Exploring the Boundaries of Video Generation Modelscited by 247
  5. 2025Seedream 4.0: Toward Next-generation Multimodal Image Generationcited by 233
  6. 2025Seedream 3.0 Technical Reportcited by 146
  7. 2023Make Pixels Dance: High-Dynamic Video Generationcited by 140
  8. 2025Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generationcited by 108
  9. 2025Seaweed-7B: Cost-Effective Training of Video Generation Foundation Modelcited by 81
  10. 2025Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Modelcited by 73
  11. 2025RewardDance: Reward Scaling in Visual Generationcited by 63
  12. 2024SeedEdit: Align Image Re-Generation to Image Editingcited by 60
2 more
  1. 2025Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Modelcited by 59
  2. 2025SeedEdit 3.0: Fast and High-Quality Generative Image Editingcited by 52

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 142.

142 papers.

Sort:

By area:

  1. 2026Motubrain: An Advanced World Action Model for Robot Controlcited by 54
  2. 2026AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routingcited by 41
  3. 2026WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluationcited by 34
  4. 2026Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Modelscited by 23
  5. 2026D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Modelscited by 17
  6. 2026Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Modelscited by 14
  7. 2026Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligencecited by 13
  8. 2026WAM4D: Fast 4D World Action Model via Spatial Register Tokenscited by 12
  9. 2026Lance: Unified Multimodal Modeling by Multi-Task Synergycited by 11
  10. 2026LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AVcited by 9
  11. 2026Leveraging Verifier-Based Reinforcement Learning in Image Editingcited by 8
  12. 2026Do Joint Audio-Video Generation Models Understand Physics?cited by 8
38 more
  1. 2026CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narrativescited by 8
  2. 2026MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generationcited by 8
  3. 2026Prisma-World: Camera-Controllable Multi-Agent Video World Modelcited by 8
  4. 2026Kairos: A Regret-Aware Native World-Action Model Stack for Physical AIcited by 8
  5. 2026WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Modelscited by 8
  6. 2026AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?cited by 7
  7. 2026Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Modelscited by 7
  8. 2026RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPOcited by 6
  9. 2026Toward Native Multimodal Modeling: A Roadmapcited by 6
  10. 2026What-If World: A Causal Benchmark for General World Models in Embodied Scenarioscited by 6
  11. 2026Native Audio-Visual Alignment for Generationcited by 6
  12. 2026LoomVideo: Unifying Multimodal Inputs into Video Generation and Editingcited by 6
  13. 2026OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Datacited by 6
  14. 2026Orca: The World is in Your Mindcited by 6
  15. 2026MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generationcited by 6
  16. 2026Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoningcited by 6
  17. 2026DySink: Dynamic Frame Sinks for Autoregressive Long Video Generationcited by 5
  18. 2026CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generationcited by 5
  19. 2026StatePlay: State-Aware Game World Models for Mechanics-Consistent Generationcited by 5
  20. 2026VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editingcited by 5
  21. 2026Marionette: Predicting World States, Rendering Geometry, Painting Appearancecited by 5
  22. 2026VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimizationcited by 4
  23. 2026Memento: Reconstruct to Remember for Consistent Long Video Generationcited by 4
  24. 2026Vidu S1: A Real-Time Interactive Video Generation Modelcited by 4
  25. 2026JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusioncited by 4
  26. 2026VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoningcited by 4
  27. 2026Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generationcited by 4
  28. 2026CoDMD: Copula-aware Distribution Matching Distillation for Fast Video Generationcited by 3
  29. 2026SteerVTE: Seamless Video Text Editing with Style and Glyph Controlcited by 3
  30. 2026A Definition and Roadmap for World Modelscited by 3
  31. 2026HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesiscited by 3
  32. 2026SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Spacecited by 3
  33. 2026HarnessEval-W: Agentifying the Evaluation of Visual Worldscited by 3
  34. 2026VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generationcited by 3
  35. 2026Magpie: Real-Time World Renderer for Interactive Gamescited by 3
  36. 2026Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generationcited by 2
  37. 2026Goodbye Drift: Anchored Tree Sampling for Long-Horizon Video-to-Video Generationcited by 2
  38. 2026On-Policy Adversarial Flow Distillation for Autoregressive Video Generationcited by 2

50 most cited of 142 All 142 (JSON)