English
Related papers

Related papers: When Do Transformers Outperform Feedforward and Re…

200 papers

We propose a machine reading comprehension model based on the compare-aggregate framework with two-staged attention that achieves state-of-the-art results on the MovieQA question answering dataset. To investigate the limitations of our…

Computation and Language · Computer Science 2018-08-28 Matthias Blohm , Glorianna Jagfeld , Ekta Sood , Xiang Yu , Ngoc Thang Vu

Transformer is the state-of-the-art model for many natural language processing, computer vision, and audio analysis problems. Transformer effectively combines information from the past input and output samples in auto-regressive manner so…

Machine Learning · Computer Science 2025-03-14 Joni-Kristian Kämäräinen

We argue that Transformers are essentially graph-to-graph models, with sequences just being a special case. Attention weights are functionally equivalent to graph edges. Our Graph-to-Graph Transformer architecture makes this ability…

Computation and Language · Computer Science 2023-10-30 James Henderson , Alireza Mohammadshahi , Andrei C. Coman , Lesly Miculicich

Feedforward neural networks (FNNs) are typically viewed as pure prediction algorithms, and their strong predictive performance has led to their use in many machine-learning applications. However, their flexibility comes with an…

Methodology · Statistics 2023-11-15 Andrew McInerney , Kevin Burke

Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks. In this work, we show that while Transformers tend to have larger model capacity, their generalization…

Computer Vision and Pattern Recognition · Computer Science 2021-09-16 Zihang Dai , Hanxiao Liu , Quoc V. Le , Mingxing Tan

In recent studies [1][13][12] Recurrent Neural Networks were used for generative processes and their surprising performance can be explained by their ability to create good predictions. In addition, data compression is also based on…

Computation and Language · Computer Science 2017-05-03 Juan Andrés Laura , Gabriel Masi , Luis Argerich

Modern deep convolutional networks (CNNs) are often criticized for not generalizing under distributional shifts. However, several recent breakthroughs in transfer learning suggest that these networks can cope with severe distribution shifts…

Despite the great success of Transformer networks in various applications such as natural language processing and computer vision, their theoretical aspects are not well understood. In this paper, we study the approximation and estimation…

Machine Learning · Computer Science 2024-03-26 Shokichi Takakura , Taiji Suzuki

Modern neural network architectures can leverage large amounts of data to generalize well within the training distribution. However, they are less capable of systematic generalization to data drawn from unseen but related distributions, a…

In this work, we analyze the capabilities and practical limitations of neural networks (NNs) for sequence-based signal processing which can be seen as an omnipresent property in almost any modern communication systems. In particular, we…

Information Theory · Computer Science 2019-11-22 Daniel Tandler , Sebastian Dörner , Sebastian Cammerer , Stephan ten Brink

Despite the remarkable success of Transformer-based architectures in various sequential modeling tasks, such as natural language processing, computer vision, and robotics, their ability to learn basic sequential models, like Hidden Markov…

Machine Learning · Computer Science 2024-06-07 Jiachen Hu , Qinghua Liu , Chi Jin

Ever since their conception, Transformers have taken over traditional sequence models in many tasks, such as NLP, image classification, and video/audio processing, for their fast training and superior performance. Much of the merit is…

Machine Learning · Computer Science 2023-02-17 Hongyu Hè , Marko Kabic

Language models with recurrent depth, also referred to as universal or looped when considering transformers, are defined by the capacity to increase their computation through the repetition of layers. Recent efforts in pretraining have…

Machine Learning · Computer Science 2025-10-17 Jonas Geiping , Xinyu Yang , Guinan Su

Transformer architectures have facilitated the development of large-scale and general-purpose sequence models for prediction tasks in natural language processing and computer vision, e.g., GPT-3 and Swin Transformer. Although originally…

Machine Learning · Computer Science 2023-06-27 Muning Wen , Runji Lin , Hanjing Wang , Yaodong Yang , Ying Wen , Luo Mai , Jun Wang , Haifeng Zhang , Weinan Zhang

Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference, especially with long inputs due to the attention mechanism's memory overhead. We observe…

Computation and Language · Computer Science 2024-10-18 Ruiqing Yan , Linghan Zheng , Xingbo Du , Han Zou , Yufeng Guo , Jianfei Yang

It is widely believed that deep neural networks contain layer specialization, wherein neural networks extract hierarchical features representing edges and patterns in shallow layers and complete objects in deeper layers. Unlike common…

Machine Learning · Computer Science 2022-03-04 Avi Schwarzschild , Arjun Gupta , Amin Ghiasi , Micah Goldblum , Tom Goldstein

Test-time scaling paradigms have significantly advanced the capabilities of large language models (LLMs) on complex tasks. Despite their empirical success, theoretical understanding of the sample efficiency of various test-time strategies…

Machine Learning · Computer Science 2025-06-13 Baihe Huang , Shanda Li , Tianhao Wu , Yiming Yang , Ameet Talwalkar , Kannan Ramchandran , Michael I. Jordan , Jiantao Jiao

Sequence modelling requires determining which past tokens are causally relevant from the context and their importance: a process inherent to the attention layers in transformers, yet whose underlying learned mechanisms remain poorly…

Machine Learning · Computer Science 2026-04-14 Francesco D'Angelo , Nicolas Flammarion

We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and capturing contexts.…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-30 Ching-Feng Yeh , Jay Mahadeokar , Kaustubh Kalgaonkar , Yongqiang Wang , Duc Le , Mahaveer Jain , Kjell Schubert , Christian Fuegen , Michael L. Seltzer

The introduction of Transformers in 2017 reshaped the landscape of deep learning. Originally proposed for sequence modelling, Transformers have since achieved widespread success across various domains. However, the scalability limitations…

Machine Learning · Computer Science 2024-12-02 Leo Feng , Frederick Tung , Mohamed Osama Ahmed , Yoshua Bengio , Hossein Hajimirsadeghi