English
Related papers

Related papers: Depth-Adaptive Transformer

200 papers

The key idea of current deep learning methods for dense prediction is to apply a model on a regular patch centered on each pixel to make pixel-wise predictions. These methods are limited in the sense that the patches are determined by…

Computer Vision and Pattern Recognition · Computer Science 2017-06-09 Jun Li , Yongjun Chen , Lei Cai , Ian Davidson , Shuiwang Ji

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

Scaling model capacity has been vital in the success of deep learning. For a typical network, necessary compute resources and training time grow dramatically with model size. Conditional computation is a promising way to increase the number…

Machine Learning · Computer Science 2018-11-14 Louis Kirsch , Julius Kunze , David Barber

Despite transformers' impressive accuracy, their computational cost is often prohibitive to use with limited computational resources. Most previous approaches to improve inference efficiency require a separate model for each possible…

Computation and Language · Computer Science 2021-06-15 Gyuwan Kim , Kyunghyun Cho

Transformer-based language models spread FLOPs uniformly across input sequences. In this work we demonstrate that transformers can instead learn to dynamically allocate FLOPs (or compute) to specific positions in a sequence, optimising the…

Machine Learning · Computer Science 2024-04-04 David Raposo , Sam Ritter , Blake Richards , Timothy Lillicrap , Peter Conway Humphreys , Adam Santoro

State-of-the-art rehearsal-free continual learning methods exploit the peculiarities of Vision Transformers to learn task-specific prompts, drastically reducing catastrophic forgetting. However, there is a tradeoff between the number of…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Thomas De Min , Massimiliano Mancini , Karteek Alahari , Xavier Alameda-Pineda , Elisa Ricci

We investigate transformer prediction of long Collatz steps, a complex arithmetic function that maps odd integers to their distant successors in the Collatz sequence ( $u_{n+1}=u_n/2$ if $u_n$ is even, $u_{n+1}=(3u_n+1)/2$ if $u_n$ is odd).…

Machine Learning · Computer Science 2025-11-17 François Charton , Ashvni Narayanan

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Machine Learning · Computer Science 2023-03-28 Quentin Fournier , Gaétan Marceau Caron , Daniel Aloise

Fine-tuning pre-trained Neural Machine Translation (NMT) models is the dominant approach for adapting to new languages and domains. However, fine-tuning requires adapting and maintaining a separate model for each target task. We propose a…

Computation and Language · Computer Science 2019-09-19 Ankur Bapna , Naveen Arivazhagan , Orhan Firat

Transformers can generate predictions in two approaches: 1. auto-regressively by conditioning each sequence element on the previous ones, or 2. directly produce an output sequences in parallel. While research has mostly explored upon this…

Computer Vision and Pattern Recognition · Computer Science 2021-08-18 Andrea Alfieri , Yancong Lin , Jan C. van Gemert

Understanding the internal mechanisms of GPT-style transformers, particularly their capacity to perform in-context learning (ICL), is critical for advancing AI alignment and interpretability. In-context learning allows transformers to…

Machine Learning · Computer Science 2024-10-24 Samarth Bhargav , Alexander Gu

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Machine Learning · Statistics 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

We explore the application of very deep Transformer models for Neural Machine Translation (NMT). Using a simple yet effective initialization technique that stabilizes training, we show that it is feasible to build standard Transformer-based…

Computation and Language · Computer Science 2020-10-16 Xiaodong Liu , Kevin Duh , Liyuan Liu , Jianfeng Gao

In spite of their huge success, transformer models remain difficult to scale in depth. In this work, we develop a unified signal propagation theory and provide formulae that govern the moments of the forward and backward signal through the…

Computation and Language · Computer Science 2024-07-19 Akhil Kedia , Mohd Abbas Zaidi , Sushil Khyalia , Jungho Jung , Harshith Goka , Haejun Lee

Transformer architectures are the backbone of the modern AI revolution. However, they are based on simply stacking the same blocks in dozens of layers and processing information sequentially from one block to another. In this paper, we…

Computation and Language · Computer Science 2024-12-24 Prateek Verma , Mert Pilanci

In this paper, we introduce the first machine learning framework for predicting optimal processing times in Single-Level Tree Network (SLTN) architectures for the Divisible Load Theory (DLT) paradigm. Using a feedforward neural network(FNN)…

Machine Learning · Computer Science 2026-05-25 Bharadwaj Veeravalli

We propose a novel approach to data-driven modeling of a transient production of oil wells. We apply the transformer-based neural networks trained on the multivariate time series composed of various parameters of oil wells measured during…

Machine Learning · Computer Science 2021-10-13 Ildar Abdrakhmanov , Evgenii Kanin , Sergei Boronin , Evgeny Burnaev , Andrei Osiptsov

Transformers have achieved great success across a wide range of applications, yet the theoretical foundations underlying their success remain largely unexplored. To demystify the strong capacities of transformers applied to versatile…

Machine Learning · Computer Science 2026-03-25 Chenyang Zhang , Qingyue Zhao , Quanquan Gu , Yuan Cao

Transformer models have consistently achieved remarkable results in various domains such as natural language processing and computer vision. However, despite ongoing research efforts to better understand these models, the field still lacks…

Machine Learning · Computer Science 2024-10-18 Ilya Kaufman , Omri Azencot

Transformers are widely used deep learning architectures. Existing transformers are mostly designed for sequences (texts or time series), images or videos, and graphs. This paper proposes a novel transformer model for massive (up to a…

Machine Learning · Computer Science 2023-11-09 Wenchong He , Zhe Jiang , Tingsong Xiao , Zelin Xu , Shigang Chen , Ronald Fick , Miles Medina , Christine Angelini