robust representations
Feature representations in AI models that are resilient to noise and variations in input data, ensuring consistent performance even when encountering unforeseen scenarios or perturbations.
- ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretraining
- AdaTS: Learning Adaptive Time Series Representations via Dynamic Soft Contrasts
- Auto-Compressing Networks
- CG-SSL: Concept-Guided Self-Supervised Learning
- CaliGCL: Calibrated Graph Contrastive Learning via Partitioned Similarity and Consistency Discrimination
- MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition
- NeurIPT: Foundation Model for Neural Interfaces
- OPTFM: A Scalable Multi-View Graph Transformer for Hierarchical Pre-Training in Combinatorial Optimization