NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
963 results for “area:"learning on time series and dynamical systems"” in ICLR 2027. 176 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Why Learn What You Can Compute? Closed-Form Operators for Periodic Time-Series Forecasting▲13k2.33
[PDF]Fast Training of Mixture-of-Experts for Time Series Forecasting via Expert Loss Integration▼1361.33
[PDF]A Multivariate Financial Time Series Foundation Model with Test-Time Learning Relational Attention▼1.2k1.67
[PDF]OICycle: Observe, Infer, and Intervene Cycle for Belief-State Learning in Longitudinal Clinical Decision Making▲11.00
[PDF]One Patch, Three Roles: What Is Actually Coupled in Autoregressive Time-Series Forecasting?▼5.9k2.50
[PDF]PKTime:Lightweight Time Series Forecasting via Kronecker-Structured Modeling with Adaptive Period Selection▼4.3k2.00
[PDF]PicardSNN: Breaking the Sequential Barrier of Spiking Neural Networks with Picard-Parallel-Training▼5.8k2.33
[PDF]Rethinking Universal Time Series Foundation Models from Unified Representations to Shared Dynamics (UniTFU)▼4.3k2.00
[PDF]FROM SCORES TO ACTIONS: CERTIFIED PROMOTION AND K > 2 CONTROL OF JOINT TIME-SERIES GENERATORS▼1.2k1.67
[PDF]Rethinking Long-Term Time Series Forecasting as Patch-to-Horizon Contribution Learning▼4.3k2.00
[PDF]PRISM: Lightweight Long-Term Time Series Forecasting with Period-Aligned Summarization▼1.2k1.67
[PDF]History-Guided Slice Self-Attention for Mitigating Forecast Smoothing in Irregular Time Series▲3.0k2.33
[PDF]Forecast residuals for the diagnosis of hidden traffic events: the ranking of normal models depends on the alarm rule▼1361.33
[PDF]Align Before Aggregation: Component-Conditioned Evidence Alignment for Multimodal Financial Forecasting▼4.3k2.00
[PDF]TimeRelay: Relation-Aware Recurrent Variable Modeling for Multivariate Time Series Forecasting▼4.5k2.67
[PDF]LG-Transformer: LLM-Guided Discovery of Boosted Novel Transformer Models for Time-Series Modeling▲11.00
[PDF]Structure, Dimensionality, and Distribution Shape: What Makes Pretraining Data Transferable, and Why the Input Pipeline Decides Which▼5.8k2.33
[PDF]PALM: Physically-Anchored Latent-timescale Mamba for Stable Representations under Distribution Shift▼5.8k2.33
[PDF]Temporal Resolution Conditions the Global–Local Trade-off in Wildfire Spread Prediction▼1.2k1.67
[PDF]OnART: Online Adaptation of Rectified Flow for Probabilistic Time-Series Forecasting with Feedback Delay▲3.0k2.33
[PDF]When Representation Change Misleads: Evaluating Encoder Adaptation in Time-Series Foundation Models▼1361.33
[PDF]From Observation Prediction to Control Coordinates: Learning Differentially Flat Latent Representations▲3952.67
Withdrawn or desk rejected (176)
[PDF]Explainable Multivariate Time-Series Anomaly Detection via Dynamic Graph Optimal TransportWithdrawn1.33
[PDF]Self-Evolving Time-Series Forecasting Agents with Episodic Memory and Online Policy LearningDesk rejected
[PDF]ERA-U: A Convention-Adaptive Evidence Interface for Window-Based Time Series ClassificationDesk rejected