paper-with-me

Papers

Spherical Position Encoding for Transformers

2023-10-04 · Eren Unlu

Position encoding is the primary mechanism which induces notion of sequential order for input tokens in transformer architectures. Even though this formulation in the original transformer paper has yielded plausible performance for general purpose language understanding and generation, several new frameworks such as Rotary Position Embedding (RoPE) are proposed for further enhancement. In this paper, we introduce the notion of "geotokens" which are input elements for transformer architectures, each representing an information related to a geological location. Unlike the natural language the sequential position is not important for the model but the geographical coordinates are. In order to induce the concept of relative position for such a setting and maintain the proportion between the physical distance and distance on embedding space, we formulate a position encoding mechanism based on RoPE architecture which is adjusted for spherical coordinates.

📄 PDF Abstract BibTeX arXiv:2310.04454

Code (0)

등록된 구현이 없습니다.

Tasks

Position

Similar Papers 제목 키워드 기반

Geotokens and Geotransformers

2024-03-23 · Eren Unlu

In transformer architectures, position encoding primarily provides a sense of sequence for input tokens. While the original transformer paper's method has shown satisfactory results in general language processing tasks, …

Position

Benchmarking Positional Encoding Strategies for Transformer-Based EEG Foundation Models

2026-05-28 · Ayse Betul Yuce, Sebastian Stober arxiv

Electroencephalography (EEG) is a widely used non-invasive technique for measuring brain activity in brain-computer interface (BCI) applications. Supervised EEG decoding models often struggle to generalize across tasks, …

Self-Supervised LearningEmotion RecognitionEeg Decoding

Herglotz-NET: Implicit Neural Representation of Spherical Data with Harmonic Positional Encoding

2025-02-19 · Théo Hanon, Nicolas Mil-Homens Cavaco, John Kiely, Laurent Jacques

Representing and processing data in spherical domains presents unique challenges, primarily due to the curvature of the domain, which complicates the application of classical Euclidean techniques. Implicit neural represe…

Comparing Graph Transformers via Positional Encodings

2024-02-22 · Mitchell Black, Zhengchao Wan, Gal Mishne, Amir Nayyeri 외

The distinguishing power of graph transformers is closely tied to the choice of positional encoding: features used to augment the base transformer with information about the graph. There are two primary types of position…

Navigate

Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional Encoding

2024-10-16 · Daichi Hayakawa, Issei Sato

In this study, we provide constructive proof that Transformers can recognize and generate hierarchical language efficiently with respect to model size, even without the need for a specific positional encoding. Specifical…