Chronicle is the first model jointly pretrained from scratch on text and time series in a unified transformer that matches a comparable language model on NLU tasks and sets new bars for time series classification and multimodal forecasting.
International Conference on Learning Representations , year =
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 7years
2026 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
LeapTS reformulates forecasting as adaptive multi-horizon scheduling via hierarchical control and NCDEs, delivering at least 7.4% better performance and 2.6-5.3x faster inference than Transformer baselines while adapting to non-stationary dynamics.
A new evaluation framework shows that blood glucose forecasting models with high overall accuracy often fail at timely hypoglycemia detection in high-risk periods and at predicting effects of changed insulin doses.
Device Passport improves cross-layout transfer for biosignal models by learning expert mixture models from each channel's functional activity and metadata, outperforming baselines in transfer regimes.
BioFormer uses spectral structural alignment via FBAM and sample-conditional normalization to improve cross-subject generalization in biomedical time-series, reporting 6% absolute F1 gains over 12 baselines on six datasets.
KUP-BI distills continuation-style knowledge from a train-only historical library to supply an approximate post-target proxy that is fused into forecasting backbones for improved performance on public datasets.
Retrieval-augmented forecasting outperforms long-context scaling in time series models on ETTh1, with an inverse scaling law where error rises as context length increases.
citing papers explorer
-
Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding
Chronicle is the first model jointly pretrained from scratch on text and time series in a unified transformer that matches a comparable language model on NLU tasks and sets new bars for time series classification and multimodal forecasting.
-
LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling
LeapTS reformulates forecasting as adaptive multi-horizon scheduling via hierarchical control and NCDEs, delivering at least 7.4% better performance and 2.6-5.3x faster inference than Transformer baselines while adapting to non-stationary dynamics.
-
From Prediction to Practice: A Task-Aware Evaluation Framework for Blood Glucose Forecasting
A new evaluation framework shows that blood glucose forecasting models with high overall accuracy often fail at timely hypoglycemia detection in high-risk periods and at predicting effects of changed insulin doses.
-
Device Passport: Enabling Spatio-Temporal Pretrained Models to Generalize Across Input Layouts
Device Passport improves cross-layout transfer for biosignal models by learning expert mixture models from each channel's functional activity and metadata, outperforming baselines in transfer regimes.
-
BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-Series
BioFormer uses spectral structural alignment via FBAM and sample-conditional normalization to improve cross-subject generalization in biomedical time-series, reporting 6% absolute F1 gains over 12 baselines on six datasets.
-
Beyond Extrapolation: Knowledge Utilization Paradigm with Bidirectional Inspiration for Time Series Forecasting
KUP-BI distills continuation-style knowledge from a train-only historical library to supply an approximate post-target proxy that is fused into forecasting backbones for improved performance on public datasets.
-
Retrieval Mechanisms Surpass Long-Context Scaling in Time Series Forecasting
Retrieval-augmented forecasting outperforms long-context scaling in time series models on ETTh1, with an inverse scaling law where error rises as context length increases.