# Motif-Video 2B: Technical Report

arXiv: https://arxiv.org/abs/2604.16503 · HTML: https://mlsanity.com/paper/2604.16503/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 44 of its 52 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Builds on (most cited first, 30 of 44)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives](https://mlsanity.com/paper/2211.04894/) (2022)
- [Seedance 1.0: Exploring the Boundaries of Video Generation Models](https://mlsanity.com/paper/2506.09113/) (2025)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [SkyReels-V2: Infinite-length Film Generative Model](https://mlsanity.com/paper/2504.13074/) (2025)
- [Video models are zero-shot learners and reasoners](https://mlsanity.com/paper/2509.20328/) (2025)
- [Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2208.09910/) (2022)
- [A Self-Supervised Descriptor for Image Copy Detection](https://mlsanity.com/paper/2202.10261/) (2022)
- [Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model](https://mlsanity.com/paper/2502.10248/) (2025)
- [Open-Sora 2.0: Training a Commercial-Level Video Generation Model in 200k](https://mlsanity.com/paper/2503.09642/) (2025)
- [HunyuanVideo 1.5 Technical Report](https://mlsanity.com/paper/2511.18870/) (2025)
- [Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content](https://mlsanity.com/paper/2410.08260/) (2024)
- [V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning](https://mlsanity.com/paper/2603.14482/) (2026)
- [Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models](https://mlsanity.com/paper/2410.02416/) (2024)
- [DDT: Decoupled Diffusion Transformer](https://mlsanity.com/paper/2504.05741/) (2025)
- [VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models](https://mlsanity.com/paper/2505.23656/) (2025)

## Abstract (arXiv)

Training strong video generation models usually requires massive datasets, large parameter counts, and substantial compute. In this work, we ask whether strong text-to-video quality is possible at a much smaller budget: fewer than 10M clips and less than 100,000 H200 GPU hours. Our core claim is that part of the answer lies in how model capacity is organized, not only in how much of it is used. In video generation, prompt alignment, temporal consistency, and fine-detail recovery can interfere with one another when they are handled through the same pathway. Motif-Video 2B addresses this by separating these roles architecturally, rather than relying on scale alone. The model combines two key ideas. First, Shared Cross-Attention strengthens text control when video token sequences become long. Second, a three-part backbone separates early fusion, joint representation learning, and detail refinement. To make this design effective under a limited compute budget, we pair it with an efficient training recipe based on dynamic token routing and early-phase feature alignment to a frozen pretrained video encoder. Our analysis shows that later blocks develop clearer cross-frame attention structure than standard single-stream baselines. On VBench, Motif-Video~2B reaches 83.76%, surpassing Wan2.1 14B while using 7× fewer parameters and substantially less training data. These results suggest that careful architectural specialization, combined with an efficiency-oriented training recipe, can narrow or exceed the quality gap typically associated with much larger video models.