Ji-Lin Hu

TFB-2: benchmarking and automated ensemble for time series forecasting

GRAM: Correcting Frozen Time-Series Foundation Models via Graph-Retrieved Amplitude Memory

Time-series foundation models (TSFMs) enable zero-shot forecasting through large-scale cross-domain pretraining, while retrieval augmentation further improves their performance by leveraging historical information. However, existing methods typically correct TSFM forecasts using the ground-truth futures of similar hist...

BITS: Rethinking Fair and Comprehensive Evaluation for Irregular Time Series Forecasting

BITS, a standardized, reproducible, and extensible benchmark for advancing research on irregular time series forecasting, is proposed and it is found that method performance varies substantially across irregularity characteristics, with no single modeling strategy consistently dominating.

FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting

In this work, we introduce FLAME, a family of extremely lightweight and capable Time Series Foundation Models, which support versatile forecasting tasks via generative probabilistic modeling, while ensuring both efficiency and robustness. FLAME utilizes the Legendre Memory for strong generalization capabilities. By ada...

WorldTS: World Modeling for Multimodal Covariate-aware Time Series Forecasting

This work proposes WorldTS, a world-modeling based forecasting framework that integrates multimodal covariates directly into the forecasting to further improve forecasting performance and employs a two-stage training strategy.

Aurora-X: Built for Extreme Time Series Forecasting

A novel pattern-guided mixture-of-experts that expands model capacity through sparse activation and uses shallow patch similarities to constrain deep-layer routing, guiding expert specialization across heterogeneous time series and an implicit quantile network head that predicts arbitrary quantiles to characterize pred...

PolarFormer: Radial-Angular Latent Modeling for Unconditional Time Series Generation

This work proposes PolarFormer, a novel framework for time series generation that addresses limitations through a polar decomposition-based discrete representation, and proposes a structurally decoupled generation strategy that models radial and angular token sequences jointly while leveraging their orthogonality to su...

WPBench: A Comprehensive Benchmark for Wind Power Forecasting

Accurate, reliable, and deployable wind power forecasting is critical for power system dispatch, renewable energy integration, and electricity market operations. Progress in this field hinges on the ability to empirically and comprehensively benchmark forecasting methods. Yet existing benchmarks fall short of supportin...

MUSE: Dependency-Aware Adaptation of a Frozen Vision Backbone for Multivariate Time Series Forecasting

This work proposes MUSE, a dependency-aware adaptation framework built on a fully frozen pretrained MAE, which performs lightweight refinement at different encoder depths and explicitly models across-period temporal dependencies and within-period periodic dependencies.

QUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability Synchronization

This work proposes QUALS, a large-scale time series corpus equilibrium framework that significantly enhances data efficiency, enabling existing models to achieve superior performance using only a small fraction of the original training data.

When Correlations Mislead: Confounder-Aware Multi-View Urban Region Representation Learning

CURE is proposed, a confounder-aware framework for multi-view urban region representation learning that improves predictive performance, remains robust under missing and noisy input views, and provides reliable cross-view integration through shared component separation and context-dependent view weighting.

REFINE: Trajectory Representation Learning via Closed-Loop Transcription

This work proposes REFINE, a simple yet effective Representation lEarning Framework that tightly couples road-network-aware generative reconstruction with feedback-driven contrastive learning, enabling the model to capture fine-grained local movement semantics and global spatio-temporal dependencies without manually de...