2 papers
cs.LG2026
Rethinking Zero-Shot Time Series Classification: From Task-specific Classifiers to In-Context Inference
Juntao Fang, Shifeng Xie, Shengbin Nie +7
The zero-shot evaluation of time series foundation models (TSFMs) for classification typically uses a frozen encoder followed by a task-specific classifier. However, this practice…
cs.CV2026
Cross-view Domain Generalization via Geometric Consistency for LiDAR Semantic Segmentation
Jindong Zhao, Yuan Gao, Yang Xia +4
Domain-generalized LiDAR semantic segmentation (LSS) seeks to train models on source-domain point clouds that generalize reliably to multiple unseen target domains, which is essent…