mlsanityData to 14 Oct 2026

Vidu S1: A Real-Time Interactive Video Generation Model

arXiv 2607.03118 ↗First posted 3 Jul 2026cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment through voice instructions. Vidu S1 supports infinite-length real-time video generation without blurring, drift, or visual distortion. Built with TurboDiffusion and TurboServe, Vidu S1 outputs 540p real-time videos at up to 42 FPS on regular consumer GPUs. Users can upload custom images of real people, anime, and pets, and choose different voice tones for personalized experiences. Experiments show that Vidu S1 achieves the best performance across all test metrics while fully meeting real-time inference requirements. A playable online demo is available at https://vidu.com/vidu-stream.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 49 of its 61 references that are in the map. First posted on arXiv 3 Jul 2026.

Builds on

49 of 61 references.

References · 49

  1. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  2. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,708
  3. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,186
  4. 2023One-step Diffusion with Distribution Matching Distillationcited by 1,019
  5. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 681
  6. 2020A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wildcited by 672
  7. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 625
  8. 2025Qwen3-Omni Technical Reportcited by 497
  9. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Modelscited by 433
  10. 2024Pyramidal Flow Matching for Efficient Video Generative Modelingcited by 366
  11. 2022Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectivescited by 320
  12. 2025MAGI-1: Autoregressive Video Generation at Scalecited by 276
37 more
  1. 2025LongLive: Real-time Interactive Long Video Generationcited by 265
  2. 2024StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Textcited by 251
  3. 2023DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Modelscited by 245
  4. 2025Rolling Forcing: Autoregressive Long Video Diffusion in Real Timecited by 234
  5. 2025SkyReels-V2: Infinite-length Film Generative Modelcited by 229
  6. 2026Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generationcited by 184
  7. 2025History-Guided Video Diffusioncited by 171
  8. 2024SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Accelerationcited by 160
  9. 2026Seedance 2.0: Advancing Video Generation for World Complexitycited by 160
  10. 2024FIFO-Diffusion: Generating Infinite Videos from Text without Trainingcited by 137
  11. 2024Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformercited by 122
  12. 2025SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inferencecited by 120
  13. 2024SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantizationcited by 114
  14. 2025Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rolloutcited by 86
  15. 2024Phased Consistency Modelscited by 85
  16. 2025Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compressioncited by 85
  17. 2025OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animationcited by 83
  18. 2024Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharingcited by 74
  19. 2024Progressive Autoregressive Video Diffusion Modelscited by 68
  20. 2025SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Trainingcited by 66
  21. 2025Wan-S2V: Audio-Driven Cinematic Video Generationcited by 61
  22. 2025SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attentioncited by 58
  23. 2026Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generationcited by 56
  24. 2025AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusioncited by 55
  25. 2025StableAvatar: Infinite-Length Audio-Driven Avatar Video Generationcited by 44
  26. 2025TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Timescited by 33
  27. 2026Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusioncited by 32
  28. 2025StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generationcited by 30
  29. 2026MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokenscited by 27
  30. 2026Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Modelscited by 25
  31. 2025SageAttention2++: A More Efficient Implementation of SageAttention2cited by 22
  32. 2026SLA2: Sparse-Linear Attention with Learnable Routing and QATcited by 22
  33. 2026SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuningcited by 18
  34. 2026LPM 1.0: Video-based Character Performance Modelcited by 11
  35. 2026SageBwd: A Trainable Low-bit Attentioncited by 8
  36. 2026Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesiscited by 6
  37. 2026TurboServe: Serving Streaming Video Generation Efficiently and Economicallycited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusioncited by 6
  2. 2026Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generationcited by 5
  3. 2026Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generationcited by 2
  4. 2026FlowAct-R2: Beyond Talking Avatar via Streaming Multimodal References and Proactive Agent Planningcited by 0