The practical performance of generative diffusion models depends on the appropriate choice of the noise scheduling function, which can also be equivalently expressed as a time reparameterization. In this paper, we present a time scheduler that selects sampling points based on entropy rather than uniform time spacing, ensuring that each point contributes an equal amount of information to the final generation. We prove that this time reparameterization does not depend on the initial choice of time. Furthermore, we provide a tractable exact formula to estimate this \emph{entropic time} for a trained model using the training loss without substantial overhead. Alongside the entropic time, inspired by the optimality results, we introduce a rescaled entropic time. In our experiments with mixtures of Gaussian distributions and ImageNet, we show that using the (rescaled) entropic times greatly improves the inference performance of trained models. In particular, we found that the image quality in pretrained EDM2 models, as evaluated by FID and FD-DINO scores, can be substantially increased by the rescaled entropic time reparameterization without increasing the number of function evaluations, with greater improvements in the few NFEs regime. Code is available at https://github.com/DejanStancevic/Entropic-Time-Schedulers-for-Generative-Diffusion-Models.
Cohomological Obstructions to Global Counterfactuals: A Sheaf-Theoretic Foundation for Generative Causal Models
School of Management, University of Science and Technology of China(管理学院,中国科学技术大学);School of Computer Science and Engineering, University of Science and Technology of China(计算机科学与工程学院,中国科学技术大学)
Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schrödinger Samplers
NVIDIA Corporation(NVIDIA公司);University of Oxford(牛津大学);Donders Institute for Brain, Cognition, and Behaviour(大脑与行为研究所);AITHYRA, Research Institute for Biomedical AI(生物医学人工智能研究所)
Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent
Laboratory for Big Data and Decision(大数据与决策实验室);National University of Defense Technology(国防科技大学);Samsung AI Center Cambridge(三星AI研究中心);Queen Mary University of London(伦敦玛丽女王大学);Fudan University(复旦大学);ShanghaiTech University(上海科技大学);Shanghai Innovation Institute(上海创新研究院)
Energy-Guided Continuous Entropic Barycenter Estimation for General Costs
Skolkovo Institute of Science and Technology(斯科尔科沃科技学院);Artificial Intelligence Research Institute(人工智能研究院);Graz University of Technology(格拉茨工业大学);Vector Institute(矢量研究院);McMaster University(麦克马斯特大学)
针对任意成本函数的连续 Entropic OT 重心估计问题,提出基于弱 OT 对偶重构与 Energy-Based Models 的新算法,具有质量界限保证、避免 min-max 优化,并在低维场景与图像流形上验证了有效性。
Diffusion-Based Impedance Learning for Contact-Rich Manipulation Tasks
Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology(人机动力学与机器人研究所,卡尔斯鲁厄技术大学);Department of Mechanical Engineering, Massachusetts Institute of Technology(机械工程系,麻省理工学院);Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology(脑与认知科学系,麻省理工学院)
From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training
California Institute of Technology(加州理工学院);NVIDIA(英伟达);Zuse Institute Berlin(柏林泽尼克研究所);dida Datenschmiede GmbH(dida数据隐私公司);Jagiellonian University(雅盖隆大学);Mila, Université de Montréal(蒙特利尔大学机器学习研究所);University of Edinburgh(爱丁堡大学);CIFAR Fellow, Learning in Machines and Brains(CIFAR Fellow, 机器学习与大脑学习)