-
DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching
Authors:
Chang Zou,
Changlin Li,
Yang Li,
Patrol Li,
Jianbing Wu,
Xiao He,
Songtao Liu,
Zhao Zhong,
Kailin Huang,
Linfeng Zhang
Abstract:
While diffusion models have achieved great success in the field of video generation, this progress is accompanied by a rapidly escalating computational burden. Among the existing acceleration methods, Feature Caching is popular due to its training-free property and considerable speedup performance, but it inevitably faces semantic and detail drop with further compression. Another widely adopted me…
▽ More
While diffusion models have achieved great success in the field of video generation, this progress is accompanied by a rapidly escalating computational burden. Among the existing acceleration methods, Feature Caching is popular due to its training-free property and considerable speedup performance, but it inevitably faces semantic and detail drop with further compression. Another widely adopted method, training-aware step-distillation, though successful in image generation, also faces drastic degradation in video generation with a few steps. Furthermore, the quality loss becomes more severe when simply applying training-free feature caching to the step-distilled models, due to the sparser sampling steps. This paper novelly introduces a distillation-compatible learnable feature caching mechanism for the first time. We employ a lightweight learnable neural predictor instead of traditional training-free heuristics for diffusion models, enabling a more accurate capture of the high-dimensional feature evolution process. Furthermore, we explore the challenges of highly compressed distillation on large-scale video models and propose a conservative Restricted MeanFlow approach to achieve more stable and lossless distillation. By undertaking these initiatives, we further push the acceleration boundaries to $11.8\times$ while preserving generation quality. Extensive experiments demonstrate the effectiveness of our method. The code will be made publicly available soon.
△ Less
Submitted 5 February, 2026; v1 submitted 5 February, 2026;
originally announced February 2026.
-
HunyuanVideo 1.5 Technical Report
Authors:
Bing Wu,
Chang Zou,
Changlin Li,
Duojun Huang,
Fang Yang,
Hao Tan,
Jack Peng,
Jianbing Wu,
Jiangfeng Xiong,
Jie Jiang,
Linus,
Patrol,
Peizhen Zhang,
Peng Chen,
Penghao Zhao,
Qi Tian,
Songtao Liu,
Weijie Kong,
Weiyan Wang,
Xiao He,
Xin Li,
Xinchi Deng,
Xuefei Zhe,
Yang Li,
Yanxin Long
, et al. (56 additional authors not shown)
Abstract:
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 til…
▽ More
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.
△ Less
Submitted 24 November, 2025; v1 submitted 24 November, 2025;
originally announced November 2025.
-
The TESS Ten Thousand Catalog: 10,001 uniformly-vetted and -validated Eclipsing Binary Stars detected in Full-Frame Image data by machine learning and analyzed by citizen scientists
Authors:
Veselin B. Kostov,
Brian P. Powell,
Aline U. Fornear,
Marco Z. Di Fraia,
Robert Gagliano,
Thomas L. Jacobs,
Julien S. de Lambilly,
Hugo A. Durantini Luca,
Steven R. Majewski,
Mark Omohundro,
Jerome Orosz,
Saul A. Rappaport,
Ryan Salik,
Donald Short,
William Welsh,
Svetoslav Alexandrov,
Cledison Marcos da Silva,
Erika Dunning,
Gerd Guhne,
Marc Huten,
Michiharu Hyogo,
Davide Iannone,
Sam Lee,
Christian Magliano,
Manya Sharma
, et al. (14 additional authors not shown)
Abstract:
The Transiting Exoplanet Survey Satellite (TESS) has surveyed nearly the entire sky in Full-Frame Image mode with a time resolution of 200 seconds to 30 minutes and a temporal baseline of at least 27 days. In addition to the primary goal of discovering new exoplanets, TESS is exceptionally capable at detecting variable stars, and in particular short-period eclipsing binaries which are relatively c…
▽ More
The Transiting Exoplanet Survey Satellite (TESS) has surveyed nearly the entire sky in Full-Frame Image mode with a time resolution of 200 seconds to 30 minutes and a temporal baseline of at least 27 days. In addition to the primary goal of discovering new exoplanets, TESS is exceptionally capable at detecting variable stars, and in particular short-period eclipsing binaries which are relatively common, making up a few percent of all stars, and represent powerful astrophysical laboratories for deep investigations of stellar formation and evolution. We combed Sectors 1-82 of TESS Full-Frame Image data searching for eclipsing binary stars using a neural network that identified ~1.2 million stars with eclipse-like features. Of these, we have performed an in-depth analysis on ~60,000 targets using automated methods and manual inspection by citizen scientists. Here we present a catalog of 10001 uniformly-vetted and -validated eclipsing binary stars that passed all our ephemeris and photocenter tests, as well as complementary visual inspection. Of these, 7936 are new eclipsing binaries while the remaining 2065 are known systems for which we update the published ephemerides. We outline the detection and analysis of the targets, discuss the properties of the sample, and highlight potentially interesting systems. Finally, we also provide a list of ~900,000 unvetted and unvalidated targets for which the neural network found eclipse-like features with a score higher than 0.9, and for which there are no known eclipsing binaries within a sky-projected separation of a TESS pixel (~21 arcsec).
△ Less
Submitted 5 June, 2025;
originally announced June 2025.