English
Related papers

Related papers: Positional Description Matters for Transformers Ar…

200 papers

Trained transformer models have been found to implement interpretable procedures for tasks like arithmetic and associative recall, but little is understood about how the circuits that implement these procedures originate during training. To…

Machine Learning · Computer Science 2024-10-08 Ziqian Zhong , Jacob Andreas

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

Several recent works use positional encodings to extend the receptive fields of graph neural network (GNN) layers equipped with attention mechanisms. These techniques, however, extend receptive fields to the complete graph, at substantial…

Machine Learning · Computer Science 2023-12-14 Rickard Brüel-Gabrielsson , Mikhail Yurochkin , Justin Solomon

Most approaches for semantic segmentation use only information from color cameras to parse the scenes, yet recent advancements show that using depth data allows to further improve performances. In this work, we focus on transformer-based…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Francesco Barbato , Giulia Rizzoli , Pietro Zanuttigh

The hardness of learning a function that attains a target task relates to its input-sensitivity. For example, image classification tasks are input-insensitive as minor corruptions should not affect the classification results, whereas…

Machine Learning · Computer Science 2025-06-26 Kazuki Yoda , Kazuhiko Kawamoto , Hiroshi Kera

Transformers achieve unrivalled performance in modelling language, but remain inefficient in terms of memory and time complexity. A possible remedy is to reduce the sequence length in the intermediate layers by pooling fixed-length segments…

Computation and Language · Computer Science 2023-10-25 Piotr Nawrot , Jan Chorowski , Adrian Łańcucki , Edoardo M. Ponti

Decimal multiplication is the task of multiplying two numbers in base $10^N.$ Specifically, we focus on the number-theoretic transform (NTT) family of algorithms. Using only portable techniques, we achieve a 3x-5x speedup over the mpdecimal…

Data Structures and Algorithms · Computer Science 2020-12-11 Viktor Krapivensky

We study the performance of transformers as a function of the number of repetitions of training examples with algorithmically generated datasets. On three problems of mathematics: the greatest common divisor, modular multiplication, and…

Machine Learning · Computer Science 2024-10-10 François Charton , Julia Kempe

We propose a novel positional encoding for learning graph on Transformer architecture. Existing approaches either linearize a graph to encode absolute position in the sequence of nodes, or encode relative position with another node using…

Machine Learning · Computer Science 2022-10-17 Wonpyo Park , Woonggi Chang , Donggeon Lee , Juntae Kim , Seung-won Hwang

Transformers have become the foundational architecture for a broad spectrum of sequence modeling applications, underpinning state-of-the-art systems in natural language processing, vision, and beyond. However, their theoretical limitations…

Computation and Language · Computer Science 2026-02-13 Michelle Yuan , Weiyi Sun , Amir H. Rezaeian , Jyotika Singh , Sandip Ghoshal , Yao-Ting Wang , Miguel Ballesteros , Yassine Benajiba

We conduct a systematic study of the approximation properties of Transformer for sequence modeling with long, sparse and complicated memory. We investigate the mechanisms through which different components of Transformer, such as the…

Machine Learning · Computer Science 2024-10-31 Mingze Wang , Weinan E

Transformers have become pivotal in Natural Language Processing, demonstrating remarkable success in applications like Machine Translation and Summarization. Given their widespread adoption, several works have attempted to analyze the…

Machine Learning · Computer Science 2024-09-02 Swaroop Nath , Harshad Khadilkar , Pushpak Bhattacharyya

Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple…

Computation and Language · Computer Science 2023-05-26 Francesco Fusco , Diego Antognini

Image inpainting has made significant advances in recent years. However, it is still challenging to recover corrupted images with both vivid textures and reasonable structures. Some specific methods only tackle regular textures while losing…

Computer Vision and Pattern Recognition · Computer Science 2022-03-17 Qiaole Dong , Chenjie Cao , Yanwei Fu

The optimal training of a vision transformer for brain encoding depends on three factors: model size, data size, and computational resources. This study investigates these three pillars, focusing on the effects of data scaling, model…

Image and Video Processing · Electrical Eng. & Systems 2024-10-29 Sana Ahmadi , Francois Paugam , Tristan Glatard , Pierre Lune Bellec

Training large language models to predict beyond their training context lengths has drawn much attention in recent years, yet the principles driving such behavior of length generalization remain underexplored. We propose a new theoretical…

Machine Learning · Computer Science 2025-02-25 Noah Golowich , Samy Jelassi , David Brandfonbrener , Sham M. Kakade , Eran Malach

Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions. However, existing neural models have been shown to lack this basic ability in learning symbolic…

Computation and Language · Computer Science 2021-10-01 Yichen Jiang , Mohit Bansal

Position representation is crucial for building position-aware representations in Transformers. Existing position representations suffer from a lack of generalization to test data with unseen lengths or high computational cost. We…

Computation and Language · Computer Science 2021-09-14 Shun Kiyono , Sosuke Kobayashi , Jun Suzuki , Kentaro Inui

Transformer has become the dominant architecture for sequence modeling, yet a detailed understanding of how its structural parameters influence expressive power remains limited. In this work, we study the approximation properties of…

Machine Learning · Computer Science 2026-04-01 Penghao Yu , Haotian Jiang , Zeyu Bao , Ruoxi Yu , Qianxiao Li

Leveraging user-provided translation to constrain NMT has practical significance. Existing methods can be classified into two main categories, namely the use of placeholder tags for lexicon words and the use of hard constraints during…

Computation and Language · Computer Science 2019-05-17 Kai Song , Yue Zhang , Heng Yu , Weihua Luo , Kun Wang , Min Zhang