English
Related papers

Related papers: Towards More Efficient Insertion Transformer with …

200 papers

Visual generative models (e.g., diffusion models) typically operate in compressed latent spaces to balance training efficiency and sample quality. In parallel, there has been growing interest in leveraging high-quality pre-trained visual…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Yuan Gao , Chen Chen , Tianrong Chen , Jiatao Gu

Transformer architectures rely on position encodings to model the spatial structure of input data. Rotary Position Encoding (RoPE) is a widely used method in language models that encodes relative positions through fixed, block-diagonal,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Sophie Ostmeier , Brian Axelrod , Maya Varma , Michael E. Moseley , Akshay Chaudhari , Curtis Langlotz

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

The Rotary Position Embedding (RoPE) mechanism has become a powerful enhancement to the Transformer architecture, which enables models to capture token relationships when encoding positional information. However, the RoPE mechanisms make…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Jiayan Huo , Yingyu Liang , Zhenmei Shi , Zhao Song

We prove under practical assumptions that Rotary Positional Embedding (RoPE) introduces an intrinsic distance-dependent bias in attention scores that limits RoPE's ability to model long-context. RoPE extension methods may alleviate this…

Computation and Language · Computer Science 2026-05-12 Yu Wang , Sheng Shen , Rémi Munos , Hongyuan Zhan , Yuandong Tian

Transformer-based end-to-end speech recognition models have received considerable attention in recent years due to their high training speed and ability to model a long-range global context. Position embedding in the transformer…

Sound · Computer Science 2021-07-14 Shengqiang Li , Menglong Xu , Xiao-Lei Zhang

Fourier features based positional encoding (PE) is commonly used in machine learning tasks that involve learning high-frequency features from low-dimensional inputs, such as 3D view synthesis and time series regression with neural tangent…

Machine Learning · Computer Science 2024-07-18 Chuanhao Sun , Zhihang Yuan , Kai Xu , Luo Mai , N. Siddharth , Shuo Chen , Mahesh K. Marina

Positional encodings are employed to capture the high frequency information of the encoded signals in implicit neural representation (INR). In this paper, we propose a novel positional encoding method which improves the reconstruction…

Computer Vision and Pattern Recognition · Computer Science 2023-11-13 Bharath Bhushan Damodaran , Francois Schnitzler , Anne Lambert , Pierre Hellier

This paper uses the Continued Fraction Expansion (CFE) method for analog realization of fractional order differ-integrator and few special classes of fractional order (FO) controllers viz. Fractional Order Proportional-Integral-Derivative…

Systems and Control · Computer Science 2016-11-30 Anindya Pakhira , Saptarshi Das , Indranil Pan , Shantanu Das

Attentional mechanisms are order-invariant. Positional encoding is a crucial component to allow attention-based deep model architectures such as Transformer to address sequences or images where the position of information matters. In this…

Machine Learning · Computer Science 2021-11-10 Yang Li , Si Si , Gang Li , Cho-Jui Hsieh , Samy Bengio

Tokenization is the first step in modern neural language model pipelines where an input text is converted to a sequence of subword tokens. We introduce from first principles a finite-state transduction framework which can efficiently encode…

Computation and Language · Computer Science 2024-10-22 Marco Cognetta , Naoaki Okazaki

Deep convolutional neural networks (CNNs) have proven highly effective for visual recognition, where learning a universal representation from activations of convolutional layer plays a fundamental problem. In this paper, we present Fisher…

Computer Vision and Pattern Recognition · Computer Science 2016-11-30 Zhaofan Qiu , Ting Yao , Tao Mei

Recent image generation models show remarkable generation performance. However, they mirror strong location preference in datasets, which we call spatial bias. Therefore, generators render poor samples at unseen locations and scales. We…

Machine Learning · Computer Science 2021-08-04 Jooyoung Choi , Jungbeom Lee , Yonghyun Jeong , Sungroh Yoon

Transformers are increasingly prevalent for multi-view computer vision tasks, where geometric relationships between viewpoints are critical for 3D perception. To leverage these relationships, multi-view transformers must use camera geometry…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Ruilong Li , Brent Yi , Junchen Liu , Hang Gao , Yi Ma , Angjoo Kanazawa

Positional Encodings (PEs) are essential for injecting structural information into Graph Neural Networks (GNNs), particularly Graph Transformers, yet their empirical impact remains insufficiently understood. We introduce a unified…

Machine Learning · Computer Science 2026-01-15 Florian Grötschla , Jiaqing Xie , Roger Wattenhofer

Positional and structural encodings (PSE) enable better identifiability of nodes within a graph, rendering them essential tools for empowering modern GNNs, and in particular graph Transformers. However, designing PSEs that work optimally…

Recent advancements in transformer-based models have greatly improved time series analysis, providing robust solutions for tasks such as forecasting, anomaly detection, and classification. A crucial element of these models is positional…

Machine Learning · Computer Science 2026-05-07 Habib Irani , Vangelis Metsis

In generative modeling, tokenization simplifies complex data into compact, structured representations, creating a more efficient, learnable space. For high-dimensional visual data, it reduces redundancy and emphasizes key features for…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Long Zhao , Sanghyun Woo , Ziyu Wan , Yandong Li , Han Zhang , Boqing Gong , Hartwig Adam , Xuhui Jia , Ting Liu

The attention mechanism is a critical component of Large Language Models (LLMs) that allows tokens in a sequence to interact with each other, but is order-invariant. Incorporating position encoding (PE) makes it possible to address by…

Computation and Language · Computer Science 2024-05-31 Olga Golovneva , Tianlu Wang , Jason Weston , Sainbayar Sukhbaatar

Efficiently encoding classical visual data into quantum states is essential for realizing practical quantum neural networks (QNNs). However, existing encoding schemes often discard spatial and semantic information when adapting…

Quantum Physics · Physics 2025-11-20 Yuhu Lu , Jinjing Shi