FlexCast introduces a flexible context-target learning framework for time series foundation models, reformulating forecasting as variable-length masked prediction over time series patches. By dynamically sampling visible context and masked target patches during pretraining, it exposes the model to diverse context-target configurations without sequential decoding. The same pretrained model can perform one-step forecasting, confidence-based iterative refinement, and next-token-style generation, achieving competitive or superior accuracy to strong TSFM baselines while reducing inference latency.
By Zuyang Shen, Luqi Gong, Fanda Fan, Bingsong Wang, Xiang Ao, Yahui Wei, Minghao Liu, Chunjie Luo, Jianfeng Zhan
The paper introduces a hybrid attention model that learns a unified time‑aware patch representation for irregular multivariate time series (IMTS) forecasting. It employs a time‑aware patch encoding to embed variable‑length intra‑patch timestamps, a time bias attention mechanism to adjust for temporal misalignment and asynchronous cross‑channel dependencies, and a hybrid causal mask on a decoder‑only Transformer to balance historical context with autoregressive forecasting. The authors also curate VersaTSA, a 30 B‑observation dataset preserving native sampling sparsity, and demonstrate state‑of‑the‑art zero‑shot performance on three IMTS benchmarks while remaining competitive on regular MTS tasks.
By Zhihao Lin, Li Lin, Qi Zhang, Kaiwen Xia, Shuai Wang, Jialin Qiao
arXiv:2607. 27656v1 Announce Type: new Abstract: Looped Transformers create a useful train- and test-time compute axis by reusing the same Transformer block over recurrent depth, increasing effective depth at a fixed parameter count.
By Bum Jun Kim, Kohei Hayashi, Shunsuke Kamiya, Masanori Koyama, Yusuke Iwasawa, Yutaka Matsuo
Adapting a forecasting system to a changing world classically means retraining. We ask whether the task of continually learning regimes for time series forecasting can be represented by a piece of tex...
The paper proposes a training‑free continual learning approach for multimodal time‑series forecasting by evolving a textual guidance block that is appended to a frozen large language model’s prompt. On a benchmark combining weekly search indices, daily currencies, and daily commodities with web‑retrieved news, the evolved 900‑word guidance outperforms existing time‑series foundation models and transfers to newer models without loss, while requiring only monetary cost rather than GPU days. The authors also show that compiling the guidance into executable code recovers most of the gain deterministically and that the advantage grows at short horizons, with news text being distilled into policy during learning.
By Laurent Mombaerts, Jonathan Taws, Jacopo Gargano, Dinesh Gaddam, Kevin George, Srijan Tiwari, Shreyas Rajesh
Text-conditioned time-series forecasting predicts a series from both its numerical history and natural-language context, allowing forecasts to account for events and constraints that the past alone cannot reveal. This requires both reliable numerical forecasting and the ability to interpret contextual information.
arXiv:2607. 24892v1 Announce Type: cross Abstract: Text-conditioned time-series forecasting predicts a series from both its numerical history and natural-language context, allowing forecasts to account for events and constraints that the past alone cannot reveal.
By Huu Hiep Nguyen, Dung Nguyen, Minh Hoang Nguyen, Dai Do, Hung Le
arXiv:2609. 20193v1 Announce Type: new Abstract: Retrieval plug-ins supply a deep forecaster with information its lookback window cannot carry.
By Mert Onur Cakiroglu, Elham Buxton, Mehmet Dalkilic, Hasan Kurban
arXiv:2609.15344v1 Announce Type: new
Abstract: We study the adaptation of pretrained language models to univariate time-series forecasting through a parameter-efficient transfer learning framework,...
By Tamanna Kumavat, Georg Brunner, Kyriakos Flouris
arXiv:2609.39386v1 Announce Type: new
Abstract: Pretrained time-series foundation models (TSFMs) are evaluated as forecasters of future values, yet for sparse series many decisions depend only on whi...
By Daniel Schoess, Florian von Wangenheim
arXiv:2610.07834v1 Announce Type: new
Abstract: Retrieval-augmented time-series forecasting uses the continuations of historical segments similar to the current context as references for a forecaster...
By Chao He, Jianyu Xu, Xinyi Guo, Ruiqi Liu, Haobin Ding, Ruiqi He, Dongqing Song
arXiv:2609.36337v1 Announce Type: new
Abstract: Tabular foundation models achieve strong performance by conditioning on labelled examples in context, but softmax attention limits their use on large d...
By David Schnurr, Felix Sarnthein, Thomas Hofmann, Imanol Schlag