English
Related papers

Related papers: Impact of Positional Encoding: Clean and Adversari…

200 papers

Positional encoding is a vital component of Transformer architectures, enabling models to incorporate sequence order into self-attention mechanisms. Rotary Positional Embeddings (RoPE) have become a widely adopted solution due to their…

Computation and Language · Computer Science 2025-08-01 Ali Veisi , Delaram Fartoot , Hamidreza Amirzadeh

Is the center position fully capable of representing a pixel? There is nothing wrong to represent pixels with their centers in a discrete image representation, but it makes more sense to consider each pixel as the aggregation of signals…

Image and Video Processing · Electrical Eng. & Systems 2021-12-14 Ying-Tian Liu , Yuan-Chen Guo , Song-Hai Zhang

In vision transformers, position embedding (PE) plays a crucial role in capturing the order of tokens. However, in vision transformer structures, there is a limitation in the expressiveness of PE due to the structure where position…

Computer Vision and Pattern Recognition · Computer Science 2025-02-06 Wonjun Lee , Bumsub Ham , Suhyun Kim

Deep networks are well-known to be fragile to adversarial attacks, and adversarial training is one of the most popular methods used to train a robust model. To take advantage of unlabeled data, recent works have applied adversarial training…

Machine Learning · Computer Science 2023-02-22 Xin Zou , Weiwei Liu

Adversarial training has been demonstrated to be one of the most effective remedies for defending adversarial examples, yet it often suffers from the huge robustness generalization gap on unseen testing adversaries, deemed as the…

Machine Learning · Computer Science 2023-03-13 Aishan Liu , Shiyu Tang , Siyuan Liang , Ruihao Gong , Boxi Wu , Xianglong Liu , Dacheng Tao

Tables are ubiquitous across various domains for concisely representing structured information. Empowering large language models (LLMs) to reason over tabular data represents an actively explored direction. However, since typical LLMs only…

Computation and Language · Computer Science 2024-10-21 Jia-Nan Li , Jian Guan , Wei Wu , Zhengtao Yu , Rui Yan

This paper studies generalization error bounds for Transformer models. Based on the offset Rademacher complexity, we derive sharper generalization bounds for different Transformer architectures, including single-layer single-head,…

Machine Learning · Computer Science 2026-03-24 Yawen Li , Tao Hu , Zhouhui Lian , Wan Tian , Yijie Peng , Huiming Zhang , Zhongyi Li

The Abstraction and Reasoning Corpus challenges AI systems to perform abstract reasoning with minimal training data, a task intuitive for humans but demanding for machine learning models. Using CodeT5+ as a case study, we demonstrate how…

Artificial Intelligence · Computer Science 2025-02-04 Guilherme H. Bandeira Costa , Miguel Freire , Arlindo L. Oliveira

Relative position encoding (RPE) is important for transformer to capture sequence ordering of input tokens. General efficacy has been proven in natural language processing. However, in computer vision, its efficacy is not well studied and…

Computer Vision and Pattern Recognition · Computer Science 2021-07-30 Kan Wu , Houwen Peng , Minghao Chen , Jianlong Fu , Hongyang Chao

This paper studies how Transformer models with Rotary Position Embeddings (RoPE) develop emergent, wavelet-like properties that compensate for the positional encoding's theoretical limitations. Through an analysis spanning model scales,…

Machine Learning · Computer Science 2025-06-06 Valeria Ruscio , Umberto Nanni , Fabrizio Silvestri

According to the principle of compositional generalization, the meaning of a complex expression can be understood as a function of the meaning of its parts and of how they are combined. This principle is crucial for human language…

Computation and Language · Computer Science 2024-03-19 Sungjun Han , Sebastian Padó

To process novel sentences, language models (LMs) must generalize compositionally -- combine familiar elements in new ways. What aspects of a model's structure promote compositional generalization? Focusing on transformers, we test the…

Computation and Language · Computer Science 2024-04-12 Jackson Petty , Sjoerd van Steenkiste , Ishita Dasgupta , Fei Sha , Dan Garrette , Tal Linzen

Scene-agnostic visual inpainting remains very challenging despite progress in patch-based methods. Recently, Pathak et al. 2016 have introduced convolutional "context encoders" (CEs) for unsupervised feature learning through image…

Computer Vision and Pattern Recognition · Computer Science 2019-04-08 Huy V. Vo , Ngoc Q. K. Duong , Patrick Perez

SinGAN shows impressive capability in learning internal patch distribution despite its limited effective receptive field. We are interested in knowing how such a translation-invariant convolutional generator could capture the global…

Computer Vision and Pattern Recognition · Computer Science 2020-12-10 Rui Xu , Xintao Wang , Kai Chen , Bolei Zhou , Chen Change Loy

Positional encodings (PEs) are essential for effective graph representation learning because they provide position awareness in inherently position-agnostic transformer architectures and increase the expressive capacity of Graph Neural…

Machine Learning · Computer Science 2025-02-04 Charilaos I. Kanatsoulis , Evelyn Choi , Stephanie Jegelka , Jure Leskovec , Alejandro Ribeiro

Auto-regressive neural sequence models have been shown to be effective across text generation tasks. However, their left-to-right decoding order prevents generation from being parallelized. Insertion Transformer (Stern et al., 2019) is an…

Computation and Language · Computer Science 2023-02-01 Zhisong Zhang , Yizhe Zhang , Bill Dolan

In this work, we explore adversarial attacks on the Variational Autoencoders (VAE). We show how to modify data point to obtain a prescribed latent code (supervised attack) or just get a drastically different code (unsupervised attack). We…

Cryptography and Security · Computer Science 2021-05-07 Anna Kuzina , Max Welling , Jakub M. Tomczak

Transformer-based multimodal large language models often exhibit in-context learning (ICL) abilities. Motivated by this phenomenon, we ask: how do transformers learn to associate information across modalities from in-context examples? We…

Computation and Language · Computer Science 2026-05-27 Yiran Huang , Karsten Roth , Quentin Bouniot , Wenjia Xu , Zeynep Akata

Transformer network architecture has proven effective in speech enhancement. However, as its core module, self-attention suffers from quadratic complexity, making it infeasible for training on long speech utterances. In practical scenarios,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-10 Qiquan Zhang , Hongxu Zhu , Xinyuan Qian , Eliathamby Ambikairajah , Haizhou Li

Quantum classifiers are vulnerable to adversarial attacks that manipulate their input classical or quantum data. A promising countermeasure is adversarial training, where quantum classifiers are trained by using an attack-aware, adversarial…

Quantum Physics · Physics 2025-04-25 Petros Georgiou , Aaron Mark Thomas , Sharu Theresa Jose , Osvaldo Simeone
‹ Prev 1 3 4 5 6 7 10 Next ›