self-attention mechanism

6 papers

• Causality-Induced Positional Encoding for Transformer-Based Representation Learning of Non-Sequential Features
• How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation
• Polyline Path Masked Attention for Vision Transformer
• Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection
• SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D Tracking
• Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era