English
Related papers

Related papers: Two Stones Hit One Bird: Bilevel Positional Encodi…

200 papers

Target encoding is an effective encoding technique of categorical variables and is often used in machine learning systems for processing tabular data sets with mixed numeric and categorical variables. Recently en enhanced version of this…

Machine Learning · Computer Science 2020-11-24 Michael Larionov

Skeleton-based Temporal Action Segmentation involves the dense action classification of variable-length skeleton sequences. Current approaches primarily apply graph-based networks to extract framewise, whole-body-level motion…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Bowen Chen , Haoyu Ji , Zhiyong Wang , Benjamin Filtjens , Chunzhuo Wang , Weihong Ren , Bart Vanrumste , Honghai Liu

The pre-trained language models have achieved great successes in various natural language understanding (NLU) tasks due to its capacity to capture the deep contextualized information in text by pre-training on large-scale corpora. One of…

Computation and Language · Computer Science 2021-06-04 Junqiu Wei , Qun Liu , Yinpeng Guo , Xin Jiang

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

Preventing the performance decay of Transformers on inputs longer than those used for training has been an important challenge in extending the context length of these models. Though the Transformer architecture has fundamentally no limits…

Global localization using onboard perception sensors, such as cameras and LiDARs, is crucial in autonomous driving and robotics applications when GPS signals are unreliable. Most approaches achieve global localization by sequential place…

Computer Vision and Pattern Recognition · Computer Science 2024-09-18 Sha Lu , Xuecheng Xu , Yuxuan Wu , Haojian Lu , Xieyuanli Chen , Rong Xiong , Yue Wang

In transformers, the positional encoding (PE) provides essential information that distinguishes the position and order amongst tokens in a sequence. Most prior investigations of PE effects on generalization were tailored to 1D input…

Machine Learning · Computer Science 2025-06-24 Takuya Ito , Luca Cocchi , Tim Klinger , Parikshit Ram , Murray Campbell , Luke Hearne

We propose a novel learning-based formulation for visual localization of vehicles that can operate in real-time in city-scale environments. Visual localization algorithms determine the position and orientation from which an image has been…

Computer Vision and Pattern Recognition · Computer Science 2022-10-31 Arthur Moreau , Thomas Gilles , Nathan Piasco , Dzmitry Tsishkou , Bogdan Stanciulescu , Arnaud de La Fortelle

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

We conducted empirical experiments to assess the transferability of a light curve transformer to datasets with different cadences and magnitude distributions using various positional encodings (PEs). We proposed a new approach to…

Rotary Position Embeddings (RoPE) have become a standard for encoding sequence order in Large Language Models (LLMs) by applying rotations to query and key vectors in the complex plane. Standard implementations, however, utilize only the…

Computation and Language · Computer Science 2025-12-09 Xiaoran Liu , Yuerong Song , Zhigeng Liu , Zengfeng Huang , Qipeng Guo , Zhaoxiang Liu , Shiguo Lian , Ziwei He , Xipeng Qiu

Discretizing speech into tokens and generating them by a decoder-only model have been a promising direction for text-to-speech (TTS) and spoken language modeling (SLM). To shorten the sequence length of speech tokens, acoustic byte-pair…

Sound · Computer Science 2024-10-30 Bohan Li , Feiyu Shen , Yiwei Guo , Shuai Wang , Xie Chen , Kai Yu

3D visual grounding aims to identify objects in 3D point cloud scenes that match specific natural language descriptions. This requires the model to not only focus on the target object itself but also to consider the surrounding environment…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Chenshu Hou , Liang Peng , Xiaopei Wu , Xiaofei He , Wenxiao Wang

Screen content coding (SCC) is becoming increasingly important in various applications, such as desktop sharing, video conferencing, and remote education. When compared to natural camera- captured content, screen content has different…

Graphics · Computer Science 2015-11-12 Haoming Chen , Ankur Saxena , Felix Fernandes

Inverse problem or parameter estimation of ordinary differential equations (ODEs), the iterative process of minimizing the mismatch between model-predicted and experimental states by tuning the parameter values within an optimization…

Systems and Control · Electrical Eng. & Systems 2026-04-21 Siddharth Prabhu , Srinivas Rangarajan , Mayuresh Kothare

Positional encodings are a core part of transformer-based models, enabling processing of sequential data without recurrence. This paper presents a theoretical framework to analyze how various positional encoding methods, including…

Machine Learning · Computer Science 2025-06-10 Yin Li

Neural encoder-decoder models have been successful in natural language generation tasks. However, real applications of abstractive summarization must consider additional constraint that a generated summary should not exceed a desired…

Computation and Language · Computer Science 2019-04-17 Sho Takase , Naoaki Okazaki

Methods for solving scientific computing and inference problems, such as kernel- and neural network-based approaches for partial differential equations (PDEs), inverse problems, and supervised learning tasks, depend crucially on the choice…

Machine Learning · Statistics 2025-10-08 Nicholas H. Nelsen , Houman Owhadi , Andrew M. Stuart , Xianjin Yang , Zongren Zou

Large language models (LLMs) experience significant performance degradation when the input exceeds the pretraining context window, primarily due to the out-of-distribution (OOD) behavior of Rotary Position Embedding (RoPE). Recent studies…

Computation and Language · Computer Science 2025-08-06 Sikui Zhang , Guangze Gao , Ziyun Gan , Chunfeng Yuan , Zefeng Lin , Houwen Peng , Bing Li , Weiming Hu

This study introduces a novel approach to terrain feature classification by incorporating spatial point pattern statistics into deep learning models. Inspired by the concept of location encoding, which aims to capture location…

Computer Vision and Pattern Recognition · Computer Science 2024-11-25 Sizhe Wang , Wenwen Li