positional encoding
- Causality-Induced Positional Encoding for Transformer-Based Representation Learning of Non-Sequential Features
- Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
- Dynamical Properties of Tokens in Self-Attention and Effects of Positional Encoding
- Orthogonal Contrastive Learning for Multi-Representation fMRI Analysis
- Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability
- Spectral Graph Neural Networks are Incomplete on Graphs with a Simple Spectrum
- Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding