activity
20192026
most citedTime Series Change Point Detection with Self-Supervised Contrastive Predictive Coding

115 citations · 401 across the 150 of their papers we have counts for

collaborators
Showing cs.LGShow all

45 papers · 1 filter

cs.LG2026

A2TTA: Anchored-and-Agile Test-Time Adaptation for Evolving Traffic Sensor Networks

Du Yin, Xiachong Lin, Yue Tan +4

Traffic forecasting is important for efficient traffic management and route planning in smart cities. Existing traffic forecasting studies typically assume fixed sensor graphs, ove…

cs.LG2026

SeisMamba: Low-Latency Single-Station Seismic Magnitude Estimation for Spatially Distributed Earthquake Early Warning

Quenton Yeo, Zhaoge Bi, Linghan Huang +3

Rapid earthquake magnitude estimation is central to earthquake early warning, yet many operational systems depend on dense regional seismic networks and region-specific calibration…

cs.LG2026

AsyTO: Asymmetric Temporal Operator for Parameter-Efficient Multivariate Time Series Forecasting

Xiachong Lin, Du Yin, Hao Xue +5

Multivariate time-series forecasting faces a structural dilemma: sharing one temporal predictor across variables is parameter-efficient but forces heterogeneous variables through a…

cs.LG2026

ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models

Kejing Wang, Toan Nguyen, Minh Hoang Nguyen +2

Effective online adaptation of vision-language-action (VLA) models remains challenging, as sparse rewards provide weak supervision for high-dimensional autoregressive action polici…

cs.LG2026

UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation

Du Yin, Hao Xue, Jinliang Deng +4

In time-series generation, existing approaches typically handcraft ortrain a separate model for each dataset, which hinders their scalability and fails to leverage shared temporal…

cs.LG2026

FOGO: Forgetting-aware Orthogonalization Optimizer

Toan Nguyen, Yang Liu, Trung Le +2

We argue that forgetting is not confined to continual learning but is a general optimization phenomenon: during standard training, dominant mini-batch gradients suppress rare but u…