arXiv Machine Learning September 30, 2026 By Chunyi Hou, Xiangfei Qiu, Hanyin Cheng, Yutong Li, Bin Yang

HALO: Enhancing Time Series Generation via Hyperspherical Latents and Masked AutoregRessive Modeling

Read the original on arXiv Machine Learning →

HALO introduces a hyperspherical VAE to constrain continuous latent representations to a fixed‑radius shell, stabilizing numerical fluctuations. It then employs a masked autoregressive model that balances parallel decoding with temporal correlation learning, reducing inference steps and improving stability. Experiments show HALO achieves state‑of‑the‑art generation performance with significantly better inference efficiency compared to existing baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 9

L-GTA: Latent Generative Modeling for Time Series Augmentation

arXiv:2507. 23615v2 Announce Type: replace-cross Abstract: Data augmentation is becoming increasingly important across various areas of time series analysis, including forecasting, classification, and anomaly detection.

By Luis Roque, Vitor Cerqueira, Carlos Soares, Luis Torgo

diffusion benchmarks

arXiv Machine Learning

Jul 28

Autoregressive One-Step Generative Modeling for Dynamical System Forecasting

arXiv:2605. 05540v2 Announce Type: replace Abstract: Fast surrogate modeling for high-dimensional physical dynamics requires more than low short-term error: useful models must roll out efficiently while preserving the statistical structure of long trajectories.

By Tianyue Yang, Xiao Xue

diffusion benchmarks

arXiv AI

1d ago

TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization

arXiv:2605.01418v2 Announce Type: replace Abstract: Time-series data are inherently multiscale, spanning diverse temporal granularities from coarse trends to fine-scale dynamics. However, existing ti...

By Seokhyun Lee, Jaeho Kim, Changjun Oh, Mihaela van der Schaar, Changhee Lee

nlp benchmarks

arXiv Machine Learning

2d ago

WorldTS: World Modeling for Multimodal Covariate-aware Time Series Forecasting

WorldTS is a new forecasting framework that models latent dynamics conditioned on multimodal covariates to improve time‑series prediction. It uses a two‑stage training process: first learning latent state dynamics from historical data and covariates, then training a decoder to map predicted latent states back to future observations. Experiments on 21 real‑world datasets demonstrate the effectiveness of this approach.

By Yuhan Zhu, Xiangfei Qiu, Hanyin Cheng, Wangmeng Shen, Chenjuan Guo, Bin Yang, Jilin Hu, Christian S. Jensen

multimodal

arXiv Machine Learning

Jul 14

CoGenCast: A Coupled Autoregressive-Flow Generative Framework for Time Series Forecasting

arXiv:2602. 03564v2 Announce Type: replace Abstract: Time series forecasting can be viewed as a generative problem that requires both semantic understanding over contextual conditions and stochastic modeling of continuous temporal dynamics.

By Mingyue Cheng, Yaguo Liu, Daoyu Wang, Xiaoyu Tao, Qi Liu

llms diffusion multimodal benchmarks

arXiv Machine Learning

Aug 7

Kastor: An efficient fine-tuning strategy for generative emulation of PDE simulations

arXiv:2608. 06107v1 Announce Type: new Abstract: Machine learning offers a promising avenue to accelerate physical simulations by replacing computationally expensive traditional Partial Differential Equation (PDE) solvers with fast, differentiable surrogate models.

By Guillaume Couairon, Alexis Jacq, Yu-Han Wu, Renu Singh, Yana Hasson, Quentin Berthet, Romuald Elie

diffusion fine-tuning benchmarks

One email a morning, machine-written

Related stories

L-GTA: Latent Generative Modeling for Time Series Augmentation

Autoregressive One-Step Generative Modeling for Dynamical System Forecasting

TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization

WorldTS: World Modeling for Multimodal Covariate-aware Time Series Forecasting

CoGenCast: A Coupled Autoregressive-Flow Generative Framework for Time Series Forecasting

Kastor: An efficient fine-tuning strategy for generative emulation of PDE simulations