mlsanityData to 14 Oct 2026

HunyuanVideo 1.5 Technical Report

arXiv 2511.18870 ↗First posted 24 Nov 2025cs.CVcited by 160

Not on the map. Why?

Cited by 51 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present HunyuanVideo 1.5, a lightweight yet powerful open-source video generation model that achieves state-of-the-art visual quality and motion coherence with only 8.3 billion parameters, enabling efficient inference on consumer-grade GPUs. This achievement is built upon several key components, including meticulous data curation, an advanced DiT architecture featuring selective and sliding tile attention (SSTA), enhanced bilingual understanding through glyph-aware text encoding, progressive pre-training and post-training, and an efficient video super-resolution network. Leveraging these designs, we developed a unified framework capable of high-quality text-to-video and image-to-video generation across multiple durations and resolutions. Extensive experiments demonstrate that this compact and proficient model establishes a new state-of-the-art among open-source video generation models. By releasing the code and model weights, we provide the community with a high-performance foundation that lowers the barrier to video creation and research, making advanced video generation accessible to a broader audience. All open-source assets are publicly available at https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5.

Key facts. Cited by 160 papers in the map (data through 14 Oct 2026). Builds on 12 of its 17 references that are in the map. First posted on arXiv 24 Nov 2025.

Builds on

12 of 17 references.

References · 12

  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. 2023Diffusion Model Alignment Using Direct Preference Optimizationcited by 790
  4. 2024FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precisioncited by 519
  5. 2022Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectivescited by 320
  6. 2025MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDEcited by 178
  7. 2025Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Modelcited by 168
  8. 2025HunyuanImage 3.0 Technical Reportcited by 149
  9. 2025Fast Video Generation with Sliding Tile Attentioncited by 128
  10. 2024SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantizationcited by 114
  11. 2024Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Renderingcited by 81
  12. 2025Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Keycited by 65

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 156.

160 papers.

Sort:

By area:

  1. 2025Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Modelcited by 80
  2. 2026Helios: Real Real-Time Long Video Generation Modelcited by 65
  3. 2026Rethinking Video Generation Model for the Embodied Worldcited by 33
  4. 2025JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimizationcited by 31
  5. 2026OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoningcited by 27
  6. 2025T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generationcited by 24
  7. 2026WorldCompass: Reinforcement Learning for Long-Horizon World Modelscited by 24
  8. 2026Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantizationcited by 23
  9. 2026SkyReels-V3 Technique Reportcited by 20
  10. 2026RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulationcited by 19
  11. 2026OmniForcing: Unleashing Real-time Joint Audio-Visual Generationcited by 16
  12. 2026Manifold-Aware Exploration for Reinforcement Learning in Video Generationcited by 15
38 more
  1. 2026Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligencecited by 15
  2. 2026Physion-Eval: Evaluating Physical Realism in Generated Video via Human Reasoningcited by 14
  3. 2026RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Timecited by 14
  4. 2026iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Frameworkcited by 14
  5. 2026WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigationcited by 14
  6. 2026EchoWM: Open and Enterable Omnimodal World Modelscited by 13
  7. 2026Mode Seeking meets Mean Seeking for Fast Long Video Generationcited by 12
  8. 2026Lance: Unified Multimodal Modeling by Multi-Task Synergycited by 12
  9. 2026TAGRPO: Boosting GRPO on Image-to-Video Generation with Direct Trajectory Alignmentcited by 10
  10. 2026Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoningcited by 10
  11. 2026Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigationcited by 10
  12. 2026RefAlign: Representation Alignment for Reference-to-Video Generationcited by 10
  13. 2026PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulationcited by 10
  14. 2026NavDreamer: Video Models as Zero-Shot 3D Navigatorscited by 9
  15. 2026Video Models Can Reason with Verifiable Rewardscited by 9
  16. 2026LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AVcited by 9
  17. 2026The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generationcited by 8
  18. 2026World2Act: Latent Action Post-Training from World Model Dynamicscited by 8
  19. 2026OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generationcited by 8
  20. 2026What-If World: A Causal Benchmark for General World Models in Embodied Scenarioscited by 8
  21. 2026Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generationcited by 8
  22. 2026Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusioncited by 7
  23. 2026Efficient Video Diffusion Models: Advancements and Challengescited by 7
  24. 2026RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPOcited by 7
  25. 2026Toward Native Multimodal Modeling: A Roadmapcited by 7
  26. 2026Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generationcited by 6
  27. 2026SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillationcited by 6
  28. 2026ImagineUAV: Aerial Vision-Language Navigation via World-Action Modeling and Kinodynamic Planningcited by 6
  29. 2026LoomVideo: Unifying Multimodal Inputs into Video Generation and Editingcited by 6
  30. 2026CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generationcited by 6
  31. 2026From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AIcited by 6
  32. 2026MaineCoon: Pursuing A Real-Time Audio-Visual Social World Modelcited by 6
  33. 2026Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Modelcited by 6
  34. 2026Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithmscited by 5
  35. 2026VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimizationcited by 5
  36. 2026Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Controlcited by 5
  37. 2026VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editingcited by 5
  38. 2026Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusioncited by 5

50 most cited of 160 All 160 (JSON)