LongCat-Video Technical Report

• URL: http://arxiv.org/abs/2510.22200v2
• Date: Tue, 28 Oct 2025 14:19:57 GMT
• Title: LongCat-Video Technical Report
• Authors: Meituan LongCat Team, Xunliang Cai, Qilong Huang, Zhuoliang Kang, Hongyu Li, Shijun Liang, Liya Ma, Siyu Ren, Xiaoming Wei, Rixu Xie, Tong Zhang,
• Abstract summary: LongCat-Video is a foundational video generation model with 13.6B parameters.<n>It supports Text-to-Video, Image-to-Video, and Video-Continuation tasks with a single model.<n>LongCat-Video generates 720p, 30fps videos within minutes by employing a coarse-to-fine generation strategy.
• Score: 40.35352541782164
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Video generation is a critical pathway toward world models, with efficient long video inference as a key capability. Toward this end, we introduce LongCat-Video, a foundational video generation model with 13.6B parameters, delivering strong performance across multiple video generation tasks. It particularly excels in efficient and high-quality long video generation, representing our first step toward world models. Key features include: Unified architecture for multiple tasks: Built on the Diffusion Transformer (DiT) framework, LongCat-Video supports Text-to-Video, Image-to-Video, and Video-Continuation tasks with a single model; Long video generation: Pretraining on Video-Continuation tasks enables LongCat-Video to maintain high quality and temporal coherence in the generation of minutes-long videos; Efficient inference: LongCat-Video generates 720p, 30fps videos within minutes by employing a coarse-to-fine generation strategy along both the temporal and spatial axes. Block Sparse Attention further enhances efficiency, particularly at high resolutions; Strong performance with multi-reward RLHF: Multi-reward RLHF training enables LongCat-Video to achieve performance on par with the latest closed-source and leading open-source models. Code and model weights are publicly available to accelerate progress in the field.

Related papers

• HunyuanVideo 1.5 Technical Report [96.9793191588414]
  HunyuanVideo 1.5 is a lightweight yet powerful open-source video generation model.<n>It achieves state-of-the-art visual quality and motion coherence with only 8.3 billion parameters.<n>All open-source assets are publicly available at https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5.
  arXiv  Detail & Related papers  (2025-11-24T08:22:07Z)
• LongLive: Real-time Interactive Long Video Generation [68.45945318075432]
  LongLive is a frame-level autoregressive framework for real-time and interactive long video generation.<n>LongLive sustains 20.7 FPS on a single NVIDIA H100, achieves strong performance on VBench in both short and long videos.
  arXiv  Detail & Related papers  (2025-09-26T17:48:24Z)
• Scaling RL to Long Videos [115.96341152407008]
  LongVILA-R1-7B achieves strong performance on video benchmarks, reaching 65.1% and 71.1% accuracy on VideoMME without and with subtitles, respectively.<n>LongVILA-R1-7B supports processing up to 8,192 video frames per video, and FPS settings.<n>We release our training system for public availability that supports RL training on various modalities.
  arXiv  Detail & Related papers  (2025-07-10T17:47:40Z)
• LongDiff: Training-Free Long Video Generation in One Go [27.38597403230757]
  LongDiff is a training-free method consisting of Position Mapping (PM) and Informative Frame Selection (IFS)<n>Our method tackles two key challenges that hinder short-to-long video generation generalization: temporal position ambiguity and information dilution.<n>Our method unlocks the potential of off-the-shelf video diffusion models to achieve high-quality long video generation in one go.
  arXiv  Detail & Related papers  (2025-03-23T17:34:57Z)
• VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling [43.485687038460895]
  Long-context video modeling is critical for multimodal large language models (MLLMs)<n>This paper aims to address this issue from aspects of model architecture, training data, training strategy and evaluation benchmark.<n>We build a powerful video MLLM named VideoChat-Flash, which shows a leading performance on both mainstream long and short video benchmarks.
  arXiv  Detail & Related papers  (2024-12-31T18:01:23Z)
• LVD-2M: A Long-take Video Dataset with Temporally Dense Captions [68.88624389174026]
  We introduce a new pipeline for selecting high-quality long-take videos and generating temporally dense captions. Specifically, we define a set of metrics to quantitatively assess video quality including scene cuts, dynamic degrees, and semantic-level quality. We curate the first long-take video dataset, LVD-2M, comprising 2 million long-take videos, each covering more than 10 seconds and annotated with temporally dense captions.
  arXiv  Detail & Related papers  (2024-10-14T17:59:56Z)
• Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input [34.50993235961505]
  Kangaroo is a powerful Video LMM aimed at addressing the challenges of processing long videos. Data curation system to build a large-scale dataset with high-quality annotations for vision-language pre-training and instruction tuning. curriculum training pipeline with gradually increasing resolution and number of input frames to accommodate long videos.
  arXiv  Detail & Related papers  (2024-08-28T05:34:14Z)
• FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention [57.651429116402554]
  This paper investigates a straightforward and training-free approach to extend an existing short video diffusion model for consistent long video generation. We find that directly applying the short video diffusion model to generate long videos can lead to severe video quality degradation. Motivated by this, we propose a novel solution named FreeLong to balance the frequency distribution of long video features during the denoising process.
  arXiv  Detail & Related papers  (2024-07-29T11:52:07Z)
• ExVideo: Extending Video Diffusion Models via Parameter-Efficient Post-Tuning [36.378348127629195]
  We propose a novel post-tuning methodology for video synthesis models, called ExVideo. This approach is designed to enhance the capability of current video synthesis models, allowing them to produce content over extended temporal durations. Our approach augments the model's capacity to generate up to $5times$ its original number of frames, requiring only 1.5k GPU hours of training on a dataset comprising 40k videos.
  arXiv  Detail & Related papers  (2024-06-20T09:18:54Z)
• Video Generation Beyond a Single Clip [76.5306434379088]
  Video generation models can only generate video clips that are relatively short compared with the length of real videos. To generate long videos covering diverse content and multiple events, we propose to use additional guidance to control the video generation process. The proposed approach is complementary to existing efforts on video generation, which focus on generating realistic video within a fixed time window.
  arXiv  Detail & Related papers  (2023-04-15T06:17:30Z)

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.