NeurIPS 2024 accepted papers on Time series
85 of the 4,560 papers accepted at NeurIPS 2024 (1.9%) are on Time series, compared with 1.5% at NeurIPS 2023. They fall into 4 topics.
See NeurIPS 2024 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
Long-term forecasting · 29 papers
- TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables (199 citations)
- SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion (89 citations)
- FilterNet: Harnessing Frequency Filters for Time Series Forecasting (37 citations)
- From Similarity to Superiority: Channel Clustering for Time Series Forecasting (37 citations)
- Are Self-Attentions Effective for Time Series Forecasting? (34 citations)
- CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns (34 citations)
- DDN: Dual-domain Dynamic Normalization for Non-stationary Time Series Forecasting (31 citations)
- Frequency Adaptive Normalization For Non-stationary Time Series Forecasting (30 citations)
- Scaling transformer neural networks for skillful and reliable medium-range weather forecasting (20 citations)
- DeformableTST: Transformer for Time Series Forecasting without Over-reliance on Patching (17 citations)
- Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting (13 citations)
- Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models (10 citations)
and 17 more in the interactive map.
Causal and generative time series · 28 papers
- Motion Forecasting in Continuous Driving (18 citations)
- Retrieval-Augmented Diffusion Models for Time Series Forecasting (15 citations)
- FIDE: Frequency-Inflated Conditional Diffusion Model for Extreme-Aware Time Series Generation (10 citations)
- TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Series (6 citations)
- ANT: Adaptive Noise Schedule for Time Series Diffusion Models (5 citations)
- Scaling Law for Time Series Forecasting (4 citations)
- SDformer: Similarity-driven Discrete Transformer For Time Series Generation (3 citations)
- Trajectory Flow Matching with Applications to Clinical Time Series Modelling (3 citations)
- A scalable generative model for dynamical system reconstruction from neuroimaging data (2 citations)
- Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting (2 citations)
- Conformalized Time Series with Semantic Features (2 citations)
- Learning diverse causally emergent representations from time series data (2 citations)
and 16 more in the interactive map.
Foundation models for time series · 25 papers
- UniTS: A Unified Multi-Task Time Series Model (57 citations)
- Are Language Models Actually Useful for Time Series Forecasting? (53 citations)
- Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification (53 citations)
- Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series (40 citations)
- AutoTimes: Autoregressive Time Series Forecasters via Large Language Models (34 citations)
- Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis (15 citations)
- From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection (13 citations)
- Large Pre-trained time series models for cross-domain Time series analysis tasks (13 citations)
- Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting (10 citations)
- PowerPM: Foundation Model for Power Systems (9 citations)
- Terra: A Multimodal Spatio-Temporal Dataset Spanning the Earth (8 citations)
- Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal Masking (5 citations)
and 13 more in the interactive map.