Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models

• URL: http://arxiv.org/abs/2503.00951v1
• Date: Sun, 02 Mar 2025 16:10:32 GMT
• Title: Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models
• Authors: Xingzhuo Guo, Yu Zhang, Baixu Chen, Haoran Xu, Jianmin Wang, Mingsheng Long,
• Abstract summary: We introduce Dynamical Diffusion (DyDiff), a theoretically sound framework that incorporates temporally aware forward and reverse processes.<n>Experiments across scientifictemporal forecasting, video prediction, and time series forecasting demonstrate that Dynamical Diffusion consistently improves performance in temporal predictive tasks.
• Score: 71.63194926457119
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models have emerged as powerful generative frameworks by progressively adding noise to data through a forward process and then reversing this process to generate realistic samples. While these models have achieved strong performance across various tasks and modalities, their application to temporal predictive learning remains underexplored. Existing approaches treat predictive learning as a conditional generation problem, but often fail to fully exploit the temporal dynamics inherent in the data, leading to challenges in generating temporally coherent sequences. To address this, we introduce Dynamical Diffusion (DyDiff), a theoretically sound framework that incorporates temporally aware forward and reverse processes. Dynamical Diffusion explicitly models temporal transitions at each diffusion step, establishing dependencies on preceding states to better capture temporal dynamics. Through the reparameterization trick, Dynamical Diffusion achieves efficient training and inference similar to any standard diffusion model. Extensive experiments across scientific spatiotemporal forecasting, video prediction, and time series forecasting demonstrate that Dynamical Diffusion consistently improves performance in temporal predictive tasks, filling a crucial gap in existing methodologies. Code is available at this repository: https://github.com/thuml/dynamical-diffusion.

Related papers

• Elucidated Rolling Diffusion Models for Probabilistic Weather Forecasting [52.6508222408558]
  We introduce Elucidated Rolling Diffusion Models (ERDM)<n>ERDM is the first framework to unify a rolling forecast structure with the principled, performant design of Elucidated Diffusion Models (EDM)<n>On 2D Navier-Stokes simulations and ERA5 global weather forecasting at 1.5circ resolution, ERDM consistently outperforms key diffusion-based baselines.
  arXiv  Detail & Related papers  (2025-06-24T21:44:31Z)
• FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation [51.110607281391154]
  FlowMo is a training-free guidance method for enhancing motion coherence in text-to-video models.<n>It estimates motion coherence by measuring the patch-wise variance across the temporal dimension and guides the model to reduce this variance dynamically during sampling.
  arXiv  Detail & Related papers  (2025-06-01T19:55:33Z)
• Consistent World Models via Foresight Diffusion [56.45012929930605]
  We argue that a key bottleneck in learning consistent diffusion-based world models lies in the suboptimal predictive ability.<n>We propose Foresight Diffusion (ForeDiff), a diffusion-based world modeling framework that enhances consistency by decoupling condition understanding from target denoising.
  arXiv  Detail & Related papers  (2025-05-22T10:01:59Z)
• Generating time-consistent dynamics with discriminator-guided image diffusion models [2.5592599835023067]
  temporal dynamics are crucial for many video generation, processing and modelling applications.<n>Video diffusion models (VDMs) are the current state-of-the-art method for generating highly realistic dynamics.<n>Here, we propose a time-consistency discriminator that enables pretrained image diffusion models to generate realistic dynamics.
  arXiv  Detail & Related papers  (2025-05-14T02:51:10Z)
• Generative Pre-trained Autoregressive Diffusion Transformer [54.476056835275415]
  GPDiT is a Generative Pre-trained Autoregressive Diffusion Transformer.<n>It unifies the strengths of diffusion and autoregressive modeling for long-range video synthesis.<n>It autoregressively predicts future latent frames using a diffusion loss, enabling natural modeling of motion dynamics.
  arXiv  Detail & Related papers  (2025-05-12T08:32:39Z)
• FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation [15.64941169350615]
  Data assimilation (DA) integrates observations with a dynamical model to estimate states of PDE-governed systems.<n>FlowDAS is a generative DA framework that uses interpolants to learn state transition dynamics.<n>We show that FlowDAS surpasses model-driven methods, neural operators, and score-based baselines in accuracy and physical plausibility.
  arXiv  Detail & Related papers  (2025-01-13T05:03:41Z)
• Auto-Regressive Moving Diffusion Models for Time Series Forecasting [2.3814052021083354]
  Time series forecasting (TSF) is essential in various domains, and recent advancements in diffusion-based TSF models have shown considerable promise. We propose a novel Auto-Regressive Moving Diffusion (ARMD) model to first achieve the continuous sequential diffusion-based TSF. Our approach reinterprets the diffusion process by considering future series as the initial state and historical series as the final state.
  arXiv  Detail & Related papers  (2024-12-12T14:51:48Z)
• Energy-Based Diffusion Language Models for Text Generation [126.23425882687195]
  Energy-based Diffusion Language Model (EDLM) is an energy-based model operating at the full sequence level for each diffusion step.<n>Our framework offers a 1.3$times$ sampling speedup over existing diffusion models.
  arXiv  Detail & Related papers  (2024-10-28T17:25:56Z)
• Unfolding Time: Generative Modeling for Turbulent Flows in 4D [49.843505326598596]
  This work introduces a 4D generative diffusion model and a physics-informed guidance technique that enables the generation of realistic sequences of flow states. Our findings indicate that the proposed method can successfully sample entire subsequences from the turbulent manifold. This advancement opens doors for the application of generative modeling in analyzing the temporal evolution of turbulent flows.
  arXiv  Detail & Related papers  (2024-06-17T10:21:01Z)
• Rolling Diffusion Models [24.25050460124981]
  Rolling Diffusion is a new approach that uses a sliding window denoising process. It ensures that the diffusion process progressively corrupts through time by assigning more noise to frames that appear later in a sequence. Empirically, we show that when the temporal dynamics are complex, Rolling Diffusion is superior to standard diffusion.
  arXiv  Detail & Related papers  (2024-02-12T08:16:10Z)
• TimeGraphs: Graph-based Temporal Reasoning [64.18083371645956]
  TimeGraphs is a novel approach that characterizes dynamic interactions as a hierarchical temporal graph. Our approach models the interactions using a compact graph-based representation, enabling adaptive reasoning across diverse time scales. We evaluate TimeGraphs on multiple datasets with complex, dynamic agent interactions, including a football simulator, the Resistance game, and the MOMA human activity dataset.
  arXiv  Detail & Related papers  (2024-01-06T06:26:49Z)
• Non-autoregressive Conditional Diffusion Models for Time Series Prediction [3.9722979176564763]
  TimeDiff is a non-autoregressive diffusion model that achieves high-quality time series prediction. We show that TimeDiff consistently outperforms existing time series diffusion models.
  arXiv  Detail & Related papers  (2023-06-08T08:53:59Z)
• Instructed Diffuser with Temporal Condition Guidance for Offline Reinforcement Learning [71.24316734338501]
  We propose an effective temporally-conditional diffusion model coined Temporally-Composable diffuser (TCD) TCD extracts temporal information from interaction sequences and explicitly guides generation with temporal conditions. Our method reaches or matches the best performance compared with prior SOTA baselines.
  arXiv  Detail & Related papers  (2023-06-08T02:12:26Z)
• DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting [18.86526240105348]
  We propose an approach for efficiently training diffusion models for probabilistic forecasting. We train a time-conditioned interpolator and a forecaster network that mimic the forward and reverse processes of standard diffusion models. Our approach performs competitively on probabilistic forecasting of complex dynamics in sea surface temperatures, Navier-Stokes flows, and flows spring systems.
  arXiv  Detail & Related papers  (2023-06-03T02:46:31Z)
• Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series [18.885471782270375]
  NCDSSM employs auxiliary variables to disentangle recognition from dynamics, thus requiring amortized inference only for the auxiliary variables. We propose three flexible parameterizations of the latent dynamics and an efficient training objective that marginalizes the dynamic states during inference. Empirical results on multiple benchmark datasets show improved imputation and forecasting performance of NCDSSM over existing models.
  arXiv  Detail & Related papers  (2023-01-26T18:45:04Z)
• How Much is Enough? A Study on Diffusion Times in Score-based Generative Models [76.76860707897413]
  Current best practice advocates for a large T to ensure that the forward dynamics brings the diffusion sufficiently close to a known and simple noise distribution. We show how an auxiliary model can be used to bridge the gap between the ideal and the simulated forward dynamics, followed by a standard reverse diffusion process.
  arXiv  Detail & Related papers  (2022-06-10T15:09:46Z)

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.