English
Related papers

Related papers: Geometry without Position? When Positional Embeddi…

200 papers

We propose a conditional positional encoding (CPE) scheme for vision Transformers. Unlike previous fixed or learnable positional encodings, which are pre-defined and independent of input tokens, CPE is dynamically generated and conditioned…

Computer Vision and Pattern Recognition · Computer Science 2023-02-14 Xiangxiang Chu , Zhi Tian , Bo Zhang , Xinlong Wang , Chunhua Shen

Recent studies have revealed various manifestations of position bias in transformer architectures, from the "lost-in-the-middle" phenomenon to attention sinks, yet a comprehensive theoretical understanding of how attention masks and…

Machine Learning · Computer Science 2025-08-12 Xinyi Wu , Yifei Wang , Stefanie Jegelka , Ali Jadbabaie

Vision transformers have established a precedent of patchifying images into uniformly-sized chunks before processing. We hypothesize that this design choice may limit models in learning comprehensive and compositional representations from…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Neha Kalibhat , Priyatham Kattakinda , Sumit Nawathe , Arman Zarei , Nikita Seleznev , Samuel Sharpe , Senthil Kumar , Soheil Feizi

Vision Transformers (ViTs) have recently dominated a range of computer vision tasks, yet it suffers from low training data efficiency and inferior local semantic representation capability without appropriate inductive bias. Convolutional…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Cong Wang , Hongmin Xu , Xiong Zhang , Li Wang , Zhitong Zheng , Haifeng Liu

Recently vision transformers (ViT) have been applied successfully for various tasks in computer vision. However, important questions such as why they work or how they behave still remain largely unknown. In this paper, we propose an…

Computer Vision and Pattern Recognition · Computer Science 2022-10-19 Van-Anh Nguyen , Khanh Pham Dinh , Long Tung Vuong , Thanh-Toan Do , Quan Hung Tran , Dinh Phung , Trung Le

Positional encodings (PEs) are essential for building powerful and expressive graph neural networks and graph transformers, as they effectively capture the relative spatial relationships between nodes. Although extensive research has been…

Machine Learning · Computer Science 2026-03-16 Yinan Huang , Haoyu Wang , Pan Li

Visual representation learning has been a cornerstone in computer vision, involving typical forms such as visual embeddings, structural symbols, and text-based representations. Despite the success of CLIP-type visual embeddings, they often…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Yiwu Zhong , Zi-Yuan Hu , Michael R. Lyu , Liwei Wang

A major factor contributing to the success of modern representation learning is the ease of performing various vector operations. Recently, objects with geometric structures (eg. distributions, complex or hyperbolic vectors, or regions such…

Computation and Language · Computer Science 2021-09-13 Tejas Chheda , Purujit Goyal , Trang Tran , Dhruvesh Patel , Michael Boratko , Shib Sankar Dasgupta , Andrew McCallum

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…

Computation and Language · Computer Science 2023-10-10 Eren Unlu

Recent progress in geospatial foundation models highlights the importance of learning general-purpose representations for real-world locations, particularly points-of-interest (POIs) where human activity concentrates. Existing approaches,…

Machine Learning · Computer Science 2026-03-06 Maria Despoina Siampou , Shushman Choudhury , Shang-Ling Hsu , Neha Arora , Cyrus Shahabi

Geometric relational embeddings map relational data as geometric objects that combine vector information suitable for machine learning and structured/relational information for structured/relational reasoning, typically in low dimensions.…

Artificial Intelligence · Computer Science 2023-04-25 Bo Xiong , Mojtaba Nayyeri , Ming Jin , Yunjie He , Michael Cochez , Shirui Pan , Steffen Staab

Vision Transformer (ViT) extends the application range of transformers from language processing to computer vision tasks as being an alternative architecture against the existing convolutional neural networks (CNN). Since the…

Computer Vision and Pattern Recognition · Computer Science 2021-08-19 Byeongho Heo , Sangdoo Yun , Dongyoon Han , Sanghyuk Chun , Junsuk Choe , Seong Joon Oh

Positional Encodings (PEs) are a critical component of Transformer-based Large Language Models (LLMs), providing the attention mechanism with important sequence-position information. One of the most popular types of encoding used today in…

Computation and Language · Computer Science 2025-05-14 Federico Barbero , Alex Vitvitskyi , Christos Perivolaropoulos , Razvan Pascanu , Petar Veličković

A common assumption in representation learning is that globally well-distributed embeddings support robust and generalizable representations. This focus has shaped both training objectives and evaluation protocols, implicitly treating…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Jiwan Chung , Seon Joo Kim

Positional encoding (PE) is a core architectural component of Transformers, yet its impact on the Transformer's generalization and robustness remains unclear. In this work, we provide the first generalization analysis for a single-layer…

Machine Learning · Statistics 2026-03-25 Weiyi He , Yue Xing

Vision Transformers (ViTs) have achieved comparable or superior performance than Convolutional Neural Networks (CNNs) in computer vision. This empirical breakthrough is even more remarkable since, in contrast to CNNs, ViTs do not embed any…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Samy Jelassi , Michael E. Sander , Yuanzhi Li

Rotary Position Embedding (RoPE) is the de facto positional encoding in large language models due to its ability to encode relative positions and support length extrapolation. When adapted to vision transformers, the standard axial…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Haoyu Liu , Sucheng Ren , Tingyu Zhu , Peng Wang , Cihang Xie , Alan Yuille , Zeyu Zheng , Feng Wang

Do autoregressive Transformer language models require explicit positional encodings (PEs)? The answer is 'no' provided they have more than one layer -- they can distinguish sequences with permuted tokens without the need for explicit PEs.…

Machine Learning · Computer Science 2025-06-03 Kazuki Irie

This paper presents the Embedding Pose Graph (EPG), an innovative method that combines the strengths of foundation models with a simple 3D representation suitable for robotics applications. Addressing the need for efficient spatial…

Robotics · Computer Science 2024-11-15 Hugues Thomas , Mouli Sivapurapu , Jian Zhang

Implicit neural representations (INRs) are increasingly being used as tools to map coordinates to signals, encompassing applications from neural fields to texture compression, shape representations, and beyond. Most INR methods are based on…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Guillaume Perez , Janarbek Matai , Takahiro Harada