mlsanityData to 14 Oct 2026

Waver: Wave Your Way to Lifelike Video Generation

arXiv 2508.15761 ↗First posted 21 Aug 2025cs.CVcited by 52

Not on the map. Why?

Cited by 22 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present Waver, a high-performance foundation model for unified image and video generation. Waver can directly generate videos with durations ranging from 5 to 10 seconds at a native resolution of 720p, which are subsequently upscaled to 1080p. The model simultaneously supports text-to-video (T2V), image-to-video (I2V), and text-to-image (T2I) generation within a single, integrated framework. We introduce a Hybrid Stream DiT architecture to enhance modality alignment and accelerate training convergence. To ensure training data quality, we establish a comprehensive data curation pipeline and manually annotate and train an MLLM-based video quality model to filter for the highest-quality samples. Furthermore, we provide detailed training and inference recipes to facilitate the generation of high-quality videos. Building on these contributions, Waver excels at capturing complex motion, achieving superior motion amplitude and temporal consistency in video synthesis. Notably, it ranks among the Top 3 on both the T2V and I2V leaderboards at Artificial Analysis (data as of 2025-07-30 10:00 GMT+8), consistently outperforming existing open-source models and matching or surpassing state-of-the-art commercial solutions. We hope this technical report will help the community more efficiently train high-quality video generation models and accelerate progress in video generation technologies. Official page: https://github.com/FoundationVision/Waver.

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). Builds on 37 of its 43 references that are in the map. First posted on arXiv 21 Aug 2025.

Builds on

37 of 43 references.

References · 37

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  6. 2022Scalable Diffusion Models with Transformerscited by 6,054
  7. 2025Qwen2.5-VL Technical Reportcited by 5,587
  8. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  9. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  10. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,708
  11. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  12. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
25 more
  1. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  2. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  3. 2021Scaling Vision Transformerscited by 999
  4. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 703
  5. 2023PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallelcited by 660
  6. 2024Movie Gen: A Cast of Media Foundation Modelscited by 644
  7. 2025VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understandingcited by 518
  8. 2025Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attentioncited by 407
  9. 2025Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Modelscited by 393
  10. 2025Seedance 1.0: Exploring the Boundaries of Video Generation Modelscited by 259
  11. 2023Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioningcited by 255
  12. 2023DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Modelscited by 245
  13. 2024Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positivecited by 241
  14. 2025Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsitycited by 217
  15. 2025Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Modelcited by 168
  16. 2025Fast Video Generation with Sliding Tile Attentioncited by 128
  17. 2024Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Modelscited by 114
  18. 2025Seaweed-7B: Cost-Effective Training of Video Generation Foundation Modelcited by 82
  19. 2025Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understandingcited by 81
  20. 2025Goku: Flow Based Video Generative Foundation Modelscited by 67
  21. 2025Model Merging in Pre-training of Large Language Modelscited by 37
  22. 2025FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generationcited by 32
  23. 2025MotionPro: A Precise Motion Controller for Image-to-Video Generationcited by 30
  24. 2025Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Thinkcited by 12
  25. 2025Dynamic-I2V: Exploring Image-to-Video Generation Models via Multimodal LLMcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 16; 2026: 36.

52 papers.

Sort:

By area:

  1. 2025Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformercited by 277
  2. 2025World Simulation with Video Foundation Models for Physical AIcited by 200
  3. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 165
  4. 2026Advancing Open-source World Modelscited by 154
  5. 2025SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformercited by 94
  6. 2025InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generationcited by 45
  7. 2025Pack and Force Your Memory: Long-form and Consistent Video Generationcited by 29
  8. 2025Region-Constraint In-Context Generation for Instructional Video Editingcited by 23
  9. 2025PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generationcited by 23
  10. 2025MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generationcited by 18
  11. 2026LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Expertscited by 15
  12. 2026Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligencecited by 15
38 more
  1. 2026Bernini: Latent Semantic Planning for Video Diffusioncited by 12
  2. 2025Scaling Zero-Shot Reference-to-Video Generationcited by 9
  3. 2026DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformercited by 9
  4. 2026ALIVE: Animate Your World with Lifelike Audio-Video Generationcited by 9
  5. 2026Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillationcited by 8
  6. 2026OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generationcited by 8
  7. 2025ID-Crafter: VLM-Grounded Online RL for Compositional Multi-Subject Video Generationcited by 6
  8. 2026A Mechanistic View on Video Generation as World Models: State and Dynamicscited by 6
  9. 2026AvatarForcing: One-Step Streaming Talking Avatars via Local-Future Sliding-Window Denoisingcited by 6
  10. 2026Echo-Memory: A Controlled Study of Memory in Action World Modelscited by 6
  11. 2026DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learningcited by 5
  12. 2026FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Spacecited by 5
  13. 2026Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithmscited by 5
  14. 2025TempoMaster: Efficient Long Video Generation via Next-Frame-Rate Predictioncited by 4
  15. 2026AR-CoPO: Align Autoregressive Video Generation with Contrastive Policy Optimizationcited by 4
  16. 2026Improving Joint Audio-Video Generation with Cross-Modal Context Learningcited by 4
  17. 2025AdaPower: Specializing World Foundation Models for Predictive Manipulationcited by 3
  18. 2025Transform Trained Transformer for Accelerating Native 4K Video Generationcited by 3
  19. 2025Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animationcited by 3
  20. 2026Research on World Models Is Not Merely Injecting World Knowledge into Specific Taskscited by 3
  21. 2026Adaptive 1D Video Diffusion Autoencodercited by 3
  22. 2026Rethinking Position Embedding as a Context Controller for Multi-Reference and Multi-Shot Video Generationcited by 3
  23. 2026Generative Refinement Networks for Visual Synthesiscited by 3
  24. 2026Image-to-Video Diffusion: From Foundations to Open Frontierscited by 3
  25. 2026Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutionscited by 3
  26. 2026Lighting-grounded Video Generation with Renderer-based Agent Reasoningcited by 2
  27. 2026PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolutioncited by 2
  28. 2025JoVA: Unified Multimodal Learning for Joint Video-Audio Generation and Editingcited by 1
  29. 2026Cross-Resolution Distribution Matching for Diffusion Distillationcited by 1
  30. 2026TransVLM: A Vision-Language Framework and Benchmark for Detecting Any Shot Transitionscited by 1
  31. 2026AdvDMD: Adversarial Reward Meets DMD For High-Quality Few-Step Generationcited by 1
  32. 2026VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priorscited by 1
  33. 2026Veda: Scalable Video Diffusion via Distilled Sparse Attentioncited by 1
  34. 2026SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generationcited by 1
  35. 2026FlashDecoder: Real-Time Latent-to-Pixel Streaming Decoder with Transformerscited by 1
  36. 2025CanvasMAR: Improving Masked Autoregressive Video Prediction With Canvascited by 0
  37. 2026Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherencecited by 0
  38. 2026Motif-Video 2B: Technical Reportcited by 0

50 most cited of 52 All 52 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
  2. 2026Alice v1: Distillation-Enhanced Video Generation Surpassing Closed-Source Models
  3. 2025VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate
  4. 2024FlexiFilm: Long Video Generation with Flexible Conditions
  5. 2025ContentV: Efficient Training of Video Generation Models with Limited Compute
  6. 2022Video Diffusion Models
  7. 2022Imagen Video: High Definition Video Generation with Diffusion Models
  8. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models