English
Related papers

Related papers: How to Dissect a Muppet: The Structure of Transfor…

200 papers

Transformer models cannot easily scale to long sequences due to their O(N^2) time and space complexity. This has led to Transformer variants seeking to lower computational complexity, such as Longformer and Performer. While such models have…

Computation and Language · Computer Science 2024-12-10 Guanghui Qin , Yukun Feng , Benjamin Van Durme

In federated learning, Transformer, as a popular architecture, faces critical challenges in defending against gradient attacks and improving model performance in both Computer Vision (CV) and Natural Language Processing (NLP) tasks. It has…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Weixin Ye , Wei Wang , Yahui Liu , Yue Song , Bin Ren , Wei Bi , Rita Cucchiara , Nicu Sebe

Transformers are widely used in state-of-the-art machine translation, but the key to their success is still unknown. To gain insight into this, we consider three groups of parameters: embeddings, attention, and feed forward neural network…

Computation and Language · Computer Science 2021-09-22 Nikolay Bogoychev

Embeddings are ubiquitous in machine learning, appearing in recommender systems, NLP, and many other applications. Researchers and developers often need to explore the properties of a specific embedding, and one way to analyze embeddings is…

The focus of past machine learning research for Reading Comprehension tasks has been primarily on the design of novel deep learning architectures. Here we show that seemingly minor choices made on (1) the use of pre-trained word embeddings,…

Computation and Language · Computer Science 2017-03-06 Bhuwan Dhingra , Hanxiao Liu , Ruslan Salakhutdinov , William W. Cohen

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

In graph representation learning, it is important that the complex geometric structure of the input graph, e.g. hidden relations among nodes, is well captured in embedding space. However, standard Euclidean embedding spaces have a limited…

Machine Learning · Computer Science 2023-07-11 Tuc Nguyen-Van , Dung D. Le , The-Anh Ta

Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternative approach in which…

Computation and Language · Computer Science 2025-05-06 Henry Ndubuaku , Mouad Talhi

After their successful debut in natural language processing, Transformer architectures are now becoming the de-facto standard in many domains. An obstacle for their deployment over new modalities is the architectural configuration: the…

Machine Learning · Computer Science 2021-06-10 Noam Wies , Yoav Levine , Daniel Jannai , Amnon Shashua

While Transformer-based models have shown impressive language modeling performance, the large computation cost is often prohibitive for practical use. Attention head pruning, which removes unnecessary attention heads in the multihead…

Computation and Language · Computer Science 2021-10-08 Kyuhong Shim , Iksoo Choi , Wonyong Sung , Jungwook Choi

Transformer layers, which use an alternating pattern of multi-head attention and multi-layer perceptron (MLP) layers, provide an effective tool for a variety of machine learning problems. As the transformer layers use residual connections…

Machine Learning · Computer Science 2022-12-13 Yaofeng Desmond Zhong , Tongtao Zhang , Amit Chakraborty , Biswadip Dey

Large language models based on the Transformer architecture have demonstrated impressive capabilities to learn in context. However, existing theoretical studies on how this phenomenon arises are limited to the dynamics of a single layer of…

Machine Learning · Statistics 2024-06-04 Juno Kim , Taiji Suzuki

We propose a synthetic reasoning task, LEGO (Learning Equality and Group Operations), that encapsulates the problem of following a chain of reasoning, and we study how the Transformer architectures learn this task. We pay special attention…

Machine Learning · Computer Science 2023-02-21 Yi Zhang , Arturs Backurs , Sébastien Bubeck , Ronen Eldan , Suriya Gunasekar , Tal Wagner

Transformers have emerged as a powerful neural network architecture capable of tackling a wide range of learning tasks. In this work, we provide a theoretical analysis of their ability to automatically extract structure from data in an…

Machine Learning · Statistics 2025-10-29 Rodrigo Maulen-Soto , Pierre Marion , Claire Boyer

Recent advancements in attention mechanisms have replaced recurrent neural networks and its variants for machine translation tasks. Transformer using attention mechanism solely achieved state-of-the-art results in sequence modeling. Neural…

Computation and Language · Computer Science 2020-04-02 Prakhar Thapak , Prodip Hore

The success of large language models (LLMs) can be attributed in part to their ability to efficiently store factual knowledge as key-value mappings within their MLP parameters. Recent work has proposed explicit weight constructions to build…

Machine Learning · Computer Science 2025-12-02 Owen Dugan , Roberto Garcia , Ronny Junkins , Jerry Liu , Dylan Zinsley , Sabri Eyuboglu , Atri Rudra , Chris Ré

Distributed word embeddings have yielded state-of-the-art performance in many NLP tasks, mainly due to their success in capturing useful semantic information. These representations assign only a single vector to each word whereas a large…

Machine Learning · Computer Science 2020-02-04 Shobhit Jain , Sravan Babu Bodapati , Ramesh Nallapati , Anima Anandkumar

This research endeavors to offer insights into unlocking the further potential of transformer-based architectures. One of the primary motivations is to offer a geometric interpretation for the attention mechanism in transformers. In our…

Machine Learning · Computer Science 2025-12-16 Zhongping Ji

Task embeddings are low-dimensional representations that are trained to capture task properties. In this paper, we propose MetaEval, a collection of $101$ NLP tasks. We fit a single transformer to all MetaEval tasks jointly while…

Computation and Language · Computer Science 2021-12-13 Damien Sileo , Marie-Francine Moens

The Transformer architecture has achieved tremendous success in natural language processing, computer vision, and scientific computing through its self-attention mechanism. However, its core components-positional encoding and attention…

Machine Learning · Computer Science 2025-11-13 Xianshuai Shi , Jianfeng Zhu , Leibo Liu
‹ Prev 1 4 5 6 7 8 10 Next ›