Motif-Video 2B: Technical Report

• URL: http://arxiv.org/abs/2604.16503v1
• Date: Tue, 14 Apr 2026 15:09:39 GMT
• Title: Motif-Video 2B: Technical Report
• Abstract summary: Training strong video generation models usually requires massive datasets, large parameter counts, and substantial compute.<n>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.
• Score: 10.684194955950353
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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$\times$ 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.

Related papers

• VideoWeave: A Data-Centric Approach for Efficient Video Understanding [54.5804686337209]
  We present VideoWeave, a simple yet effective approach to improve data efficiency by constructing synthetic long-context training samples.<n>VideoWeave reorganizes available video-text pairs to expand temporal diversity within fixed compute.<n>Our results highlight that reorganizing training data, rather than altering architectures, may offer a simple and scalable path for training video-language models.
  arXiv  Detail & Related papers  (2026-01-09T20:55:26Z)
• Generative Video Matting [57.186684844156595]
  Video matting has traditionally been limited by the lack of high-quality ground-truth data.<n>Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations.<n>We introduce a novel video matting approach that can effectively leverage the rich priors from pre-trained video diffusion models.
  arXiv  Detail & Related papers  (2025-08-11T12:18:55Z)
• Frame-Level Captions for Long Video Generation with Complex Multi Scenes [52.12699618126831]
  We propose a novel way to annotate datasets at the frame-level.<n>This detailed guidance works with a Frame-Level Attention Mechanism to make sure text and video match precisely.<n>Our training uses Diffusion Forcing to provide the model with the ability to handle time flexibly.
  arXiv  Detail & Related papers  (2025-05-27T07:39:43Z)
• TinyLLaVA-Video: Towards Smaller LMMs for Video Understanding with Group Resampler [10.92767902813594]
  We introduce TinyLLaVA-Video, a lightweight yet powerful video understanding model with approximately 3.6B parameters.<n>The cornerstone of our design is the video-level group resampler, a novel mechanism that significantly reduces and controls the number of visual tokens at the video level.<n>TinyLLaVA-Video demonstrates exceptional efficiency, requiring only one day of training on 8 A100-40G GPUs.
  arXiv  Detail & Related papers  (2025-01-26T13:10:12Z)
• A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames [57.758863967770594]
  We build on the common paradigm of transferring large-scale, image--text models to video via shallow temporal fusion.<n>We expose two limitations to the approach: (1) decreased spatial capabilities, likely due to poor video--language alignment in standard video datasets, and (2) higher memory consumption, bottlenecking the number of frames that can be processed.
  arXiv  Detail & Related papers  (2023-12-12T16:10:19Z)
• VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking [57.552798046137646]
  Video masked autoencoder (VideoMAE) is a scalable and general self-supervised pre-trainer for building video foundation models. We successfully train a video ViT model with a billion parameters, which achieves a new state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-03-29T14:28:41Z)
• VA-RED$^2$: Video Adaptive Redundancy Reduction [64.75692128294175]
  We present a redundancy reduction framework, VA-RED$2$, which is input-dependent. We learn the adaptive policy jointly with the network weights in a differentiable way with a shared-weight mechanism. Our framework achieves $20% - 40%$ reduction in computation (FLOPs) when compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-02-15T22:57:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.