ICML 2025 accepted papers on Time series
69 of the 3,342 papers accepted at ICML 2025 (2.1%) are on Time series, compared with 2.0% at ICML 2024. They fall into 4 topics.
See ICML 2025 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Foundation models for time series · 25 papers
- Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting (10 citations)
- VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters (3 citations)
- Sundial: A Family of Highly Capable Time Series Foundation Models (2 citations)
- Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization (1 citation)
- LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization (1 citation)
- Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts (1 citation)
- AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting
- BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling
- Context is Key: A Benchmark for Forecasting with Essential Textual Information
- Efficient Personalized Adaptation for Physiological Signal Foundation Model
- Exploring Representations and Interventions in Time Series Foundation Models
- FIC-TSC: Learning Time Series Classification with Fisher Information Constraint
and 13 more in the interactive map.
Long-term forecasting · 22 papers
- TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting (4 citations)
- TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation (2 citations)
- TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting (1 citation)
- TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state (1 citation)
- $K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting
- Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting
- Channel Normalization for Time Series Channel Identification
- CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations
- Efficient Time Series Processing for Transformers and State-Space Models through Token Merging
- Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive Forecasting
- Patch-wise Structural Loss for Time Series Forecasting
- Rethinking Time Encoding via Learnable Transformation Functions
and 10 more in the interactive map.
Causal and generative time series · 19 papers
- Retrieval Augmented Time Series Forecasting (2 citations)
- Risk and cross validation in ridge regression with correlated samples (2 citations)
- Relational Conformal Prediction for Correlated Time Series (1 citation)
- Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation
- Learning with Expected Signatures: Theory and Applications
- LETS Forecast: Learning Embedology for Time Series Forecasting
- LSCD: Lomb--Scargle Conditioned Diffusion for Time series Imputation
- Non-stationary Diffusion For Probabilistic Time Series Forecasting
- Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting
- SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting
- TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation
- Winner-takes-all for Multivariate Probabilistic Time Series Forecasting
and 7 more in the interactive map.