mlsanityData to 14 Oct 2026

Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model

arXiv 2512.13507 ↗First posted 15 Dec 2025cs.CVcited by 80

On the map: LLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment

Abstract (arXiv)

Recent strides in video generation have paved the way for unified audio-visual generation. In this work, we present Seedance 1.5 pro, a foundational model engineered specifically for native, joint audio-video generation. Leveraging a dual-branch Diffusion Transformer architecture, the model integrates a cross-modal joint module with a specialized multi-stage data pipeline, achieving exceptional audio-visual synchronization and superior generation quality. To ensure practical utility, we implement meticulous post-training optimizations, including Supervised Fine-Tuning (SFT) on high-quality datasets and Reinforcement Learning from Human Feedback (RLHF) with multi-dimensional reward models. Furthermore, we introduce an acceleration framework that boosts inference speed by over 10X. Seedance 1.5 pro distinguishes itself through precise multilingual and dialect lip-syncing, dynamic cinematic camera control, and enhanced narrative coherence, positioning it as a robust engine for professional-grade content creation. Seedance 1.5 pro is now accessible on Volcano Engine at https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?type=GenVideo.

Key facts. Cited by 80 papers in the map (data through 14 Oct 2026). Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 15 of its 16 references that are in the map. First posted on arXiv 15 Dec 2025.

Builds on

15 of 16 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025RewardDance: Reward Scaling in Visual Generation10 Sep
  2. 2025DanceGRPO: Unleashing GRPO on Visual Generation12 May

Other references · 13

  1. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  2. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,708
  3. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  4. 2025Qwen-Image Technical Reportcited by 1,044
  5. 2025Flow-GRPO: Training Flow Matching Models via Online RLcited by 661
  6. 2025Mean Flows for One-step Generative Modelingcited by 561
  7. 2025Seedance 1.0: Exploring the Boundaries of Video Generation Modelscited by 259
  8. 2025Seedream 4.0: Toward Next-generation Multimodal Image Generationcited by 249
  9. 2025HunyuanVideo 1.5 Technical Reportcited by 160
  10. 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesiscited by 156
  11. 2025Seedream 3.0 Technical Reportcited by 154
  12. 2025Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Modelcited by 62
1 more
  1. 2025RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectoriescited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 78.

80 papers.

Sort:

By area:

  1. 2026Seedance 2.0: Advancing Video Generation for World Complexitycited by 160
  2. 2026Advancing Open-source World Modelscited by 154
  3. 2026WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluationcited by 39
  4. 2026Rethinking Video Generation Model for the Embodied Worldcited by 33
  5. 2025T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generationcited by 24
  6. 2026SkyReels-V3 Technique Reportcited by 20
  7. 2026DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generationcited by 20
  8. 2026SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing modelcited by 12
  9. 2025PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generationcited by 11
  10. 2026PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulationcited by 10
  11. 2026Leveraging Verifier-Based Reinforcement Learning in Image Editingcited by 9
  12. 2026The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generationcited by 8
38 more
  1. 2026OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generationcited by 8
  2. 2026What-If World: A Causal Benchmark for General World Models in Embodied Scenarioscited by 8
  3. 2026JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusioncited by 7
  4. 2026MentisOculi: Revealing the Limits of Reasoning with Mental Imagerycited by 7
  5. 2026VII: Visual Instruction Injection for Jailbreaking Image-to-Video Generation Modelscited by 7
  6. 2026Efficient Video Diffusion Models: Advancements and Challengescited by 7
  7. 2026OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generationcited by 7
  8. 2026RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPOcited by 7
  9. 2026Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Modelcited by 6
  10. 2026MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hintscited by 5
  11. 2026AVControl: Efficient Framework for Training Audio-Visual Controlscited by 5
  12. 2026Continuous Adversarial Flow Modelscited by 5
  13. 2026AVBench: Human-Aligned and Automated Evaluation Benchmark for Audio-Video Generative Modelscited by 5
  14. 2026VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimizationcited by 5
  15. 2026Beyond End-to-End Video Models: An LLM-Based Multi-Agent System for Educational Video Generationcited by 4
  16. 2026DVD: Deterministic Video Depth Estimation with Generative Priorscited by 4
  17. 2026LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attentioncited by 4
  18. 2026Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worldscited by 4
  19. 2026OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generationcited by 3
  20. 2026AesRM: Improving Video Aesthetics with Expert-Level Feedbackcited by 3
  21. 2026Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformerscited by 3
  22. 2026World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestrationcited by 3
  23. 2026OpenCoF: Learning to Reason Through Video Generationcited by 3
  24. 2026BWM: A Low-Cost High-Fidelity World Simulator for Robot Learningcited by 3
  25. 2026Advances in GRPO for Generation Models: A Surveycited by 2
  26. 2026LibraGen: Playing a Balance Game in Subject-Driven Video Generationcited by 2
  27. 2026AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priorscited by 2
  28. 2026ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?cited by 2
  29. 2026How Far Are Video Models from True Multimodal Reasoning?cited by 2
  30. 2026ViPO: Visual Preference Optimization at Scalecited by 2
  31. 2026TMD-Bench: A Multi-Level Evaluation Paradigm for Music-Dance Co-Generationcited by 2
  32. 2026Audio-Visual Intelligence in Large Foundation Modelscited by 2
  33. 2026SyncDPO: Enhancing Temporal Synchronization in Video-Audio Joint Generation via Preference Learningcited by 2
  34. 2026MoWorld: A Flash World Modelcited by 2
  35. 2026KineBench: Benchmarking Embodied World Models via IDM-Free Kinematic Groundingcited by 2
  36. 2026InteracVid: Building a Real Interactive Audio-Visual Response Dataset from Live-Chat Videoscited by 2
  37. 2026Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generationcited by 2
  38. 2026EruDiff: Refactoring Knowledge in Diffusion Models for Advanced Text-to-Image Synthesiscited by 1

50 most cited of 80 All 80 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution
  2. 2026Efficient Audio-Visual Generation via Synchrony-Aware Cross-Modal Sparse Attention
  3. 2026HarmoniDPO: Video-guided Audio Generation via Preference-Optimized Diffusion
  4. 2026Diffusion Models for Joint Audio-Video Generation
  5. 2026Soundwich: Video Generation with Layered and Controllable Audio
  6. 2026MOVA: Towards Scalable and Synchronized Video-Audio Generation
  7. 2026Inference-Time Scaling for Joint Audio-Video Generation
  8. 2026FlowPortrait: Reinforcement Learning for Audio-Driven Portrait Video Generation