ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space

• URL: http://arxiv.org/abs/2604.27443v2
• Date: Tue, 05 May 2026 15:16:38 GMT
• Title: ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space
• Abstract summary: We propose ABC: Any-Subset Autoregressive Models via Non-Markovian Diffusion Bridges in Continuous Time and Space.<n>We model the process with one continual SDE whose time variable and intermediate states track the real time and process states.<n>Our experiments show ABC's superiority to competing methods on multiple domains, including video generation and weather forecasting.
• Score: 37.1234207870965
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating continuous-time, continuous-space stochastic processes (e.g., videos, weather forecasts) conditioned on partial observations (e.g., first and last frames) is a fundamental challenge. Existing approaches, (e.g., diffusion models), suffer from key limitations: (1) noise-to-data evolution fails to capture structural similarity between states close in physical time and has unstable integration in low-step regimes; (2) random noise injected is insensitive to the physical process's time elapsed, resulting in incorrect dynamics; (3) they overlook conditioning on arbitrary subsets of states (e.g., irregularly sampled timesteps, future observations). We propose ABC: Any-Subset Autoregressive Models via Non-Markovian Diffusion Bridges in Continuous Time and Space. Crucially, we model the process with one continual SDE whose time variable and intermediate states track the real time and process states. This has provable advantages: (1) the starting point for generating future states is the already-close previous state, rather than uninformative noise; (2) random noise injection scales with physical time elapsed, encouraging physically plausible dynamics with similar time-adjacent states. We derive SDE dynamics via changes-of-measure on path space, yielding another advantage: (3) path-dependent conditioning on arbitrary subsets of the state history and/or future. To learn these dynamics, we derive a path- and time-dependent extension of denoising score matching. Our experiments show ABC's superiority to competing methods on multiple domains, including video generation and weather forecasting.

Related papers

• Thinking with Looped Flows [19.42368401391554]
  Humans and machines often solve harder problems by spending more time on computation.<n>In deep learning, looped models implement this idea during inference by recurrently updating a hidden state.<n>We propose looped flows, an approach that sidesteps this issue by training the recurrence with local denoising objectives.
  arXiv  Detail & Related papers  (2026-09-10T16:52:54Z)
• ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing [24.41363445015799]
  We introduce ForcingDAS, a unified and robust data assimilation framework.<n>ForcingDAS learns a joint-trajectory prior instead of frame-to-frame transitions.<n>We evaluate ForcingDAS on 2D Navier-Stokes vorticity, precipitation nowcasting, and global atmospheric state estimation.
  arXiv  Detail & Related papers  (2026-05-14T02:34:33Z)
• HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising [52.237486207964245]
  HiAR is a hierarchical denoising framework that reverses the conventional generation order.<n>It performs causal generation across all blocks at every denoising step, so that each block is always conditioned on context at the same noise level.<n>On VBench (20s generation), HiAR achieves the best overall score and the lowest temporal drift among all compared methods.
  arXiv  Detail & Related papers  (2026-03-09T17:58:16Z)
• From Observations to States: Latent Time Series Forecasting [65.98504021691666]
  We propose Latent Time Series Forecasting (LatentTSF), a novel paradigm that shifts TSF from observation regression to latent state prediction.<n>Specifically, LatentTSF employs an AutoEncoder to project observations at each time step into a higher-dimensional latent state space.<n>Our proposed latent objectives implicitly maximize mutual information between predicted latent states and ground-truth states and observations.
  arXiv  Detail & Related papers  (2026-01-30T20:39:44Z)
• Noisy dynamics of Gaussian entanglement: a transient bound entangled phase before separability [4.058640482068898]
  We find a new class of Gaussian bound entangled states of four-mode continuous-variable systems.<n>These states appear as a transient phase when certain NPT-entangled Gaussian states are evolved under a noisy environment.
  arXiv  Detail & Related papers  (2025-03-16T23:41:10Z)
• Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models [71.63194926457119]
  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.
  arXiv  Detail & Related papers  (2025-03-02T16:10:32Z)
• Bridging discrete and continuous state spaces: Exploring the Ehrenfest process in time-continuous diffusion models [4.186575888568896]
  We study time-continuous Markov jump processes on discrete state spaces. We show that the time-reversal of the Ehrenfest process converges to the time-reversed Ornstein-Uhlenbeck process.
  arXiv  Detail & Related papers  (2024-05-06T15:12:51Z)
• Nonstationary Time Series Forecasting via Unknown Distribution Adaptation [22.915008205203886]
  As environments evolve, temporal distribution shifts can degrade time series forecasting performance.<n>Some methods disentangle stationary and nonstationary components by assuming uniform distribution shifts, but it is impractical since when the distribution changes is unknown.<n>We propose the textbfUnknown textbfDistribution textbfAdaptation (textbfUDA) model for nonstationary time series forecasting.
  arXiv  Detail & Related papers  (2024-02-20T07:16:12Z)
• RoHM: Robust Human Motion Reconstruction via Diffusion [58.63706638272891]
  RoHM is an approach for robust 3D human motion reconstruction from monocular RGB(-D) videos. It conditioned on noisy and occluded input data, reconstructs complete, plausible motions in consistent global coordinates. Our method outperforms state-of-the-art approaches qualitatively and quantitatively, while being faster at test time.
  arXiv  Detail & Related papers  (2024-01-16T18:57:50Z)
• Nonparametric and Regularized Dynamical Wasserstein Barycenters for Sequential Observations [16.05839190247062]
  We consider probabilistic models for sequential observations which exhibit gradual transitions among a finite number of states. We numerically solve a finite dimensional estimation problem using cyclic descent alternating between updates to the pure-state quantile functions and the barycentric weights. We demonstrate the utility of the proposed algorithm in segmenting both simulated and real world human activity time series.
  arXiv  Detail & Related papers  (2022-10-04T21:39:55Z)
• Dynamical Wasserstein Barycenters for Time-series Modeling [16.212262513825717]
  Most prior work assumes instantaneous transitions between pure discrete states. We propose a Wasserstein barycentric (DWB) model that estimates the system state over time. Experiments on several human activity datasets show that our proposed DWB model accurately learns the generating distribution of pure states.
  arXiv  Detail & Related papers  (2021-10-13T14:20:06Z)
• Interval-censored Hawkes processes [82.87738318505582]
  We propose a model to estimate the parameters of a Hawkes process in interval-censored settings. We show how a non-homogeneous approximation to the Hawkes admits a tractable likelihood in the interval-censored setting.
  arXiv  Detail & Related papers  (2021-04-16T07:29:04Z)

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.