arXiv Machine Learning August 17, 2026 By Dat Nguyen-Cong, Luong Tran, Tung Kieu

When Denoising Hurts: Rethinking the Terminal Step of Diffusion Time Series Forecasters -- Extended Version

Read the original on arXiv Machine Learning →

arXiv:2608. 14067v1 Announce Type: new Abstract: Diffusion models offer a natural way to model uncertainty in time series forecasting, yet their iterative sampling process is often treated as a uniformly beneficial refinement procedure.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

diffusion

arXiv AI

Jul 28

Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting

arXiv:2607. 22599v1 Announce Type: new Abstract: Diffusion models have become a widely used framework for probabilistic time series forecasting, modeling the distribution of future values given an observed history.

By Chen Su, Yuanhe Tian, Yan Song

diffusion benchmarks

arXiv AI

Jun 3

Latent Laplace Diffusion for Irregular Multivariate Time Series

arXiv:2605. 19805v2 Announce Type: replace-cross Abstract: Irregular multivariate time series impose a trade-off for long-horizon forecasting: discrete methods can distort temporal structure via re-gridding, while continuous-time models often require sequential solvers prone to drift.

By Zinuo You, Jin Zheng, John Cartlidge

diffusion

arXiv AI

Aug 12

Two-stage Odd Residual Flows for Mean-Preserving Probabilistic Time Series Forecasting

arXiv:2608. 11114v1 Announce Type: cross Abstract: Probabilistic forecasting plays an essential role in risk-sensitive decision-making, particularly in long-horizon settings.

By Kiran Madhusudhanan, Christian Kl\"otergens, Lars Schmidt-Thieme, Vijaya Krishna Yalavarthi

diffusion benchmarks

arXiv Machine Learning

Jun 16

Towards a Unified Generative Model for Scarce Time Series with Domain Experts

arXiv:2606. 15172v1 Announce Type: new Abstract: Synthesizing realistic time series with generative models has wide-ranging applications in real-world scenarios.

By Zihao Yao, Qi Zheng, Jiankai Zuo, Yaying Zhang

llms diffusion fine-tuning

arXiv Machine Learning

Jun 16

Temporal Difference Learning for Diffusion Models

arXiv:2606. 15048v1 Announce Type: new Abstract: Diffusion models are typically trained with objectives that focus on local denoising targets at individual time steps (or adjacent pairs), which do not enforce consistency between predictions along the denoising trajectory.

By Qizhen Ying, Yangchen Pan, Victor Adrian Prisacariu, Junfeng Wen

diffusion reinforcement-learning benchmarks

arXiv Machine Learning

Jul 21

DiFA: Inference-Time Forward-Process Alignment for Diffusion Models

arXiv:2607. 17972v1 Announce Type: new Abstract: The prevailing inference framework for diffusion models formulates generation fundamentally as a problem of numerical integration.

By Shigui Li, Delu Zeng

diffusion safety

Related stories

Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting

Latent Laplace Diffusion for Irregular Multivariate Time Series

Two-stage Odd Residual Flows for Mean-Preserving Probabilistic Time Series Forecasting

Towards a Unified Generative Model for Scarce Time Series with Domain Experts

Temporal Difference Learning for Diffusion Models

DiFA: Inference-Time Forward-Process Alignment for Diffusion Models