HALO is proposed, which enhances time series generation via Hyperspherical Latents and Masked Autoregressive modeling to achieve this goal by tackling two key bottlenecks: variance and scale heterogeneity of continuous latent representations and the difficulty of balancing generation efficiency with temporal correlation modeling.
Abstract
Most existing time series generators rely on a two-stage modeling paradigm: the first stage learns discrete latent representations of time series; the second stage performs autoregressive modeling on these discrete latents through next token prediction. However, this paradigm suffers from two stage-specific limitations: the first stage can lead to information loss when discretizing continuous time series, while the second stage is prone to error accumulation during autoregressive generation. To address these limitations, our core idea is to perform generative modeling in a continuous latent space with a more efficient autoregressive framework. We propose HALO, which enhances time series generation via Hyperspherical Latents and Masked Autoregressive modeling to achieve this goal by tackling two key bottlenecks: (1) variance and scale heterogeneity of continuous latent representations; (2) the difficulty of balancing generation efficiency with temporal correlation modeling. HALO first introduces a hyperspherical VAE that constrains continuous latents to a fixed-radius hyperspherical shell, effectively stabilizing the numerical fluctuations of continuous latent representations. Secondly, we develop a masked autoregressive model that balances parallel decoding and temporal correlation learning, substantially reducing the number of inference steps required for generation and improving generation stability. Our extensive experiments demonstrate that HALO achieves state-of-the-art generation performance while offering significantly improved inference efficiency over existing advanced baselines.
Generative modeling has shown strong promise for multivariate time mseries (MTS) forecasting, especially scale to high-dimensional settings. Diffusion-based methods achieve competitive performance but typically require many sampling steps at inference. VAE-based non-iterative forecasting frameworks have therefore emerg...
Shi-Bo Feng, Wan-Jin Feng, Yang Qiu et al.· 0 citations
DrafTS, a model-agnostic framework that aims to reduce noise while preserving evolving dynamics through time-aware Decomposition with ResiduAl correction For Time Series, is proposed.
Yi-Qiu Liu, Si-Ru Zhong, Zhi-Guang Wang et al.· 0 citations
The proposed COFE (COarse And FinE latent dynamics disentanglement), a variational autoencoder–based framework that models the temporal distribution by disentangling and modeling the rapidly changing and slowly varying latent dynamics simultaneously, is proposed.
Chang-Ze Zhou, Rui-Chu Cai, Sheng Nie et al.· IJCAI/ECAI· 0 citations
Neural Koopman autoencoder models have been shown to successfully build a latent embedding with linear dynamics for arbitrary dynamical systems, enabling strong performance in long-term time series forecasting. However, these models usually work in a deterministic setting, which does not allow the quantification of the...
Anthony Frion, L. Drumetz, G. Tochon et al.· arXiv.org· 0 citations
SphereVAE is proposed, which constrains the VAE latent space to the unit hypersphere and regularizes the latent distribution toward a uniform prior, so that information is encoded mainly by directional variation, providing a bounded geometric target for autoregressive prediction and reducing the risk of norm drift.
Hao-Yu Zhang, Jing-Bin Hu, Han-Ke Xie et al.· 0 citations
This work proposes WorldTS, a world-modeling based forecasting framework that integrates multimodal covariates directly into the forecasting to further improve forecasting performance and employs a two-stage training strategy.
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026