Beyond Masks: Efficient, Flexible Diffusion Language Models via Deletion-Insertion Processes

Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift

Disentangling Domain and General Representations for Time Series Classification

DWLR: Domain Adaptation under Label Shift for Wearable Sensor

Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting

Learning causal relations from subsampled time series with two time-slices

SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention

LightGTS: A Lightweight General Time Series Forecasting Model

OpenPyRo-A1: An Open Python-Based Low-Cost Bimanual Robot for Embodied AI

ManGo: Learning design-score manifold to guide diffusion models for offline optimization