mlsanityData to 7 Oct 2026

Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation

arXiv 2609.11638 ↗First posted 10 Sep 2026cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We present Vidu S2, which comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Editing, a real-time video editing model. Moreover, we explore the feasibility of real-time spatial video generation for both Vidu S2-Avatar and Vidu S2-Editing. Compared with Vidu S1, Vidu S2-Avatar supports real-time 720p video generation, generation with dynamic references that can be updated at any moment, and stronger instruction following, such as dancing. Vidu S2-Editing supports editing a video stream in real time, including style rendering, clothing replacement, character replacement, and background replacement. Experiments show that Vidu S2 outperforms all baselines. A playable online demo is available at https://vidu.com/vidu-stream.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 53 of its 67 references that are in the map. First posted on arXiv 10 Sep 2026.

Builds on

53 of 67 references.

References · 53

  1. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  2. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,204
  3. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  4. 2023Diffusion Model Alignment Using Direct Preference Optimizationcited by 767
  5. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 648
  6. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 634
  7. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 569
  8. 2025VACE: All-in-One Video Creation and Editingcited by 467
  9. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Modelscited by 401
  10. 2023DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Modelscited by 239
  11. 2025LongLive: Real-time Interactive Long Video Generationcited by 237
  12. 2025DiffusionNFT: Online Diffusion Reinforcement with Forward Processcited by 204
38 more
  1. 2023StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-Oncited by 173
  2. 2024SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Accelerationcited by 158
  3. 2024OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-oncited by 150
  4. 2026Seedance 2.0: Advancing Video Generation for World Complexitycited by 142
  5. 2024SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantizationcited by 113
  6. 2025SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inferencecited by 113
  7. 2024Improving Diffusion Models for Authentic Virtual Try-on in the Wildcited by 109
  8. 2024Synchformer: Efficient Synchronization from Sparse Cuescited by 94
  9. 2025SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Trainingcited by 63
  10. 2025SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attentioncited by 55
  11. 2025OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editingcited by 50
  12. 2024ViViD: Video Virtual Try-on using Diffusion Modelscited by 38
  13. 2024StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videoscited by 36
  14. 2026Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidancecited by 34
  15. 2025TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Timescited by 31
  16. 2025StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generationcited by 27
  17. 2026VINO: A Unified Visual Generator with Interleaved OmniModal Contextcited by 26
  18. 2025NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priorscited by 25
  19. 2026OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoningcited by 25
  20. 2025SageAttention2++: A More Efficient Implementation of SageAttention2cited by 21
  21. 2026SLA2: Sparse-Linear Attention with Learnable Routing and QATcited by 21
  22. 2026SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuningcited by 16
  23. 2026LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editingcited by 15
  24. 2025Accurate INT8 Training Through Dynamic Block-Level Fallbackcited by 14
  25. 2026Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillationcited by 13
  26. 2026LPM 1.0: Video-based Character Performance Modelcited by 11
  27. 2026Bernini: Latent Semantic Planning for Video Diffusioncited by 11
  28. 2025SoulX-FlashTalk: Real-Time Infinite Streaming of Audio-Driven Avatars via Self-Correcting Bidirectional Distillationcited by 10
  29. 2026SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editingcited by 8
  30. 2026SageBwd: A Trainable Low-bit Attentioncited by 7
  31. 2026SCAIL-2: Unifying Controlled Character Animation with End-to-End In-Context Conditioningcited by 7
  32. 2026AvatarForcing: One-Step Streaming Talking Avatars via Local-Future Sliding-Window Denoisingcited by 6
  33. 2026Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memorycited by 6
  34. 2026Vidu S1: A Real-Time Interactive Video Generation Modelcited by 4
  35. 2026JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusioncited by 4
  36. 2026StreamAV-Bench: A Comprehensive Benchmark for Streaming Audio-Video Generationcited by 4
  37. 2026TurboServe: Serving Streaming Video Generation Efficiently and Economicallycited by 3
  38. 2026CoinVE-200K: A Large-Scale High-Quality Dataset for Compositional Instruction-Guided Video Editingcited by 2

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026FlowAct-R2: Beyond Talking Avatar via Streaming Multimodal References and Proactive Agent Planningcited by 0
  2. 2026LongTake: Learning to Sustain Dynamics in Long-Horizon Video Generationcited by 0
  3. 2026UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generationcited by 0
  4. 2026Connected Self Forcing: Beyond Local Learning in Video Autoregressioncited by 0