Long input windows are required to identify the generative process in time series forecasting even for short-memory processes, and decoupling identification from forecasting improves scalability.
Foundation models for time series: A survey
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Time series foundation models match the performance of specialized models for day-ahead load forecasting while providing explanations that match domain knowledge on weather and calendar effects.
FeDPM learns and aligns local discrete prototypical memories across domains to create a unified discrete latent space for LLM-based time series foundation models in a federated setting.
TRACE proposes a temporal conditional estimation paradigm for multimodal time series foundation models that infers incomplete target modalities from auxiliary ones, outperforming prior fusion methods on clinical and sentiment benchmarks under missingness.
The proposed framework decomposes retrieval-augmented representations into invariant and dynamic components to improve robustness in zero-shot time series forecasting under distribution shifts.
Fusing chart visualizations with raw time series improves or maintains classification accuracy on UCR datasets when the visuals add non-redundant information.
Zero-shot TSFMs conditioned on leakage-safe covariates from Google Trends and an institutional index forecast commencing enrolments competitively with classical methods under data sparsity.
Falcon-X introduces a latent prototype space with Unified Prototype Diff-Attention and Latent Entity Attention for heterogeneous multivariate time series forecasting.
Eywa enables language-based agentic AI systems to collaborate with specialized scientific foundation models for improved performance on structured data tasks.
The paper envisions AI-native 6G networks anchored by a foundation model and multi-agent systems to shift network management to a unified multi-modal optimization problem.
citing papers explorer
-
Why Do Time Series Models Need Long Context Windows?
Long input windows are required to identify the generative process in time series forecasting even for short-memory processes, and decoupling identification from forecasting improves scalability.
-
Explainable Load Forecasting with Covariate-Informed Time Series Foundation Models
Time series foundation models match the performance of specialized models for day-ahead load forecasting while providing explanations that match domain knowledge on weather and calendar effects.
-
Discrete Prototypical Memories for Federated Time Series Foundation Models
FeDPM learns and aligns local discrete prototypical memories across domains to create a unified discrete latent space for LLM-based time series foundation models in a federated setting.
-
TRACE: A Temporal Conditional Estimation for Multimodal Time Series Foundation Models
TRACE proposes a temporal conditional estimation paradigm for multimodal time series foundation models that infers incomplete target modalities from auxiliary ones, outperforming prior fusion methods on clinical and sentiment benchmarks under missingness.
-
Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series Forecasting
The proposed framework decomposes retrieval-augmented representations into invariant and dynamic components to improve robustness in zero-shot time series forecasting under distribution shifts.
-
VTBench: A Multimodal Framework for Time-Series Classification with Chart-Based Representations
Fusing chart visualizations with raw time series improves or maintains classification accuracy on UCR datasets when the visuals add non-redundant information.
-
Forecasting Commencing Enrolments Under Data Sparsity: A Zero-Shot Time Series Foundation Models Framework for Higher Education Planning
Zero-shot TSFMs conditioned on leakage-safe covariates from Google Trends and an institutional index forecast commencing enrolments competitively with classical methods under data sparsity.
-
Falcon-X: A Time Series Foundation Model for Heterogeneous Multivariate Modeling
Falcon-X introduces a latent prototype space with Unified Prototype Diff-Attention and Latent Entity Attention for heterogeneous multivariate time series forecasting.
-
Heterogeneous Scientific Foundation Model Collaboration
Eywa enables language-based agentic AI systems to collaborate with specialized scientific foundation models for improved performance on structured data tasks.
-
Towards Resilient and Autonomous Networks: A BlueSky Vision on AI-Native 6G
The paper envisions AI-native 6G networks anchored by a foundation model and multi-agent systems to shift network management to a unified multi-modal optimization problem.
- TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis