English
Related papers

Related papers: Simplifying Transformer Blocks

200 papers

Transformers are the de-facto choice for sequence modelling, yet their quadratic self-attention and weak temporal bias can make long-range forecasting both expensive and brittle. We introduce FreezeTST, a lightweight hybrid that interleaves…

Machine Learning · Computer Science 2025-10-21 Pradeep Singh , Mehak Sharma , Anupriya Dey , Balasubramanian Raman

The recent surge in Time Series Foundation Models has rapidly advanced the field, yet the heterogeneous training setups across studies make it difficult to attribute improvements to architectural innovations versus data engineering. In this…

Machine Learning · Computer Science 2026-02-09 Yunshi Wen , Wesley M. Gifford , Chandra Reddy , Lam M. Nguyen , Jayant Kalagnanam , Anak Agung Julius

The attention mechanism in its standard implementation contains extraneous rotational degrees of freedom that are carried through computation but do not affect model activations or outputs. We introduce a simple symmetry-breaking protocol…

Machine Learning · Computer Science 2026-02-13 Eva Silverstein , Daniel Kunin , Vasudev Shyam

Effective license plate recognition systems are required to be resilient to constant change, as new license plates are released into traffic daily. While Transformer-based networks excel in their recognition at first sight, we observe…

Computer Vision and Pattern Recognition · Computer Science 2025-10-16 Florent Meyer , Laurent Guichard , Denis Coquenet , Guillaume Gravier , Yann Soullard , Bertrand Coüasnon

In this work, we explore whether modeling recurrence into the Transformer architecture can both be beneficial and efficient, by building an extremely simple recurrent module into the Transformer. We compare our model to baselines following…

Computation and Language · Computer Science 2022-05-25 Tao Lei , Ran Tian , Jasmijn Bastings , Ankur P. Parikh

The fast growing capabilities of large-scale deep learning models, such as Bert, GPT and ViT, are revolutionizing the landscape of NLP, CV and many other domains. Training such models, however, poses an unprecedented demand for computing…

Machine Learning · Computer Science 2024-04-15 Longwei Zou , Han Zhang , Yangdong Deng

We show that the core components of the Transformer block -- attention, residual connections, and normalization -- arise naturally from a single geometric estimation problem. Modeling the latent state as a direction on the hypersphere, with…

Machine Learning · Computer Science 2026-05-13 Peter Racioppo

Transformer models have achieved promising results on natural language processing (NLP) tasks including extractive question answering (QA). Common Transformer encoders used in NLP tasks process the hidden states of all input tokens in the…

Computation and Language · Computer Science 2022-05-17 Yue Guan , Zhengyi Li , Jingwen Leng , Zhouhan Lin , Minyi Guo , Yuhao Zhu

It is a common belief that training deep transformers from scratch requires large datasets. Consequently, for small datasets, people usually use shallow and simple additional layers on top of pre-trained models during fine-tuning. This work…

Computation and Language · Computer Science 2021-06-01 Peng Xu , Dhruv Kumar , Wei Yang , Wenjie Zi , Keyi Tang , Chenyang Huang , Jackie Chi Kit Cheung , Simon J. D. Prince , Yanshuai Cao

Recently, Transformer-based language models have demonstrated remarkable performance across many NLP domains. However, the unsupervised pre-training step of these models suffers from unbearable overall computational expenses. Current…

Machine Learning · Computer Science 2020-10-27 Minjia Zhang , Yuxiong He

We propose a convex and fast signal reconstruction method for block sparsity under arbitrary linear transform with unknown block structure. The proposed method is a generalization of the similar existing method and can reconstruct signals…

Machine Learning · Computer Science 2024-02-14 Takanobu Furuhashi , Hidekata Hontani , Tatsuya Yokota

In this article, we investigate the potential of multilevel approaches to accelerate the training of transformer architectures. Using an ordinary differential equation (ODE) interpretation of these architectures, we propose an appropriate…

Machine Learning · Computer Science 2025-04-29 Guillaume Lauga , Maël Chaumette , Edgar Desainte-Maréville , Étienne Lasalle , Arthur Lebeurrier

At typical context lengths, the feed-forward MLP block accounts for a large share of a transformer's compute budget, motivating sparse alternatives to dense MLP blocks. We study sparse, tree-structured feed-forward layers as drop-in…

Computation and Language · Computer Science 2026-04-13 Reza Sedghi , Robin Schiewer , Anand Subramoney , David Kappel

Transformers have transformed modern machine learning, driving breakthroughs in computer vision, natural language processing, and robotics. At the core of their success lies the attention mechanism, which enables the modeling of global…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Hemanth Saratchandran , Simon Lucey

Hierarchical structures are popular in recent vision transformers, however, they require sophisticated designs and massive datasets to work well. In this paper, we explore the idea of nesting basic local transformers on non-overlapping…

Computer Vision and Pattern Recognition · Computer Science 2022-01-03 Zizhao Zhang , Han Zhang , Long Zhao , Ting Chen , Sercan O. Arik , Tomas Pfister

Fine-tuning pre-trained transformers is a powerful technique for enhancing the performance of base models on specific tasks. From early applications in models like BERT to fine-tuning Large Language Models (LLMs), this approach has been…

Computation and Language · Computer Science 2025-02-25 Suneel Nadipalli

Transformer networks have seen great success in natural language processing and machine vision, where task objectives such as next word prediction and image classification benefit from nuanced context sensitivity across high-dimensional…

Machine Learning · Computer Science 2022-12-13 Yuxuan Li , James L. McClelland

Traditional machine learning excels on static benchmarks, but the real world is dynamic and seldom as carefully curated as test sets. Practical applications may generally encounter undesired inputs, are required to deal with novel…

Machine Learning · Computer Science 2025-03-17 Roshni . R. Kamath , Rupert Mitchell , Subarnaduti Paul , Kristian Kersting , Martin Mundt

The Transformer architecture has dominated machine learning in a wide range of tasks. The specific characteristic of this architecture is an expensive scaled dot-product attention mechanism that models the inter-token interactions, which is…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Zizhao Hu , Mohammad Rostami

Skip connection, is a widely-used technique to improve the performance and the convergence of deep neural networks, which is believed to relieve the difficulty in optimization due to non-linearity by propagating a linear component through…

Machine Learning · Computer Science 2021-05-18 Fenglin Liu , Xuancheng Ren , Zhiyuan Zhang , Xu Sun , Yuexian Zou