English
Related papers

Related papers: Transformer Layers as Painters

200 papers

Pretrained Transformer based models finetuned on domain specific corpora have changed the landscape of NLP. However, training or fine-tuning these models for individual tasks can be time consuming and resource intensive. Thus, a lot of…

Recurrent Neural Networks were, until recently, one of the best ways to capture the timely dependencies in sequences. However, with the introduction of the Transformer, it has been proven that an architecture with only attention-mechanisms…

Machine Learning · Computer Science 2021-08-19 Radostin Cholakov , Todor Kolev

Transformer-based large language models have achieved remarkable performance across various natural language processing tasks. However, they often struggle with seemingly easy tasks like arithmetic despite their vast capabilities. This…

Computation and Language · Computer Science 2024-07-23 Luyu Qiu , Jianing Li , Chi Su , Chen Jason Zhang , Lei Chen

Transformers achieve state-of-the-art accuracy and robustness across many tasks, but an understanding of their inductive biases and how those biases differ from other neural network architectures remains elusive. In this work, we identify…

Machine Learning · Computer Science 2025-02-14 Bhavya Vasudeva , Deqing Fu , Tianyi Zhou , Elliott Kau , Youqi Huang , Vatsal Sharan

We find limits to the Transformer architecture for language modeling and show it has a universal prediction property in an information-theoretic sense. We further analyze performance in non-asymptotic data regimes to understand the role of…

Machine Learning · Computer Science 2023-07-18 Sourya Basu , Moulik Choraria , Lav R. Varshney

Pretrained molecular encoders have become indispensable in computational chemistry for tasks such as property prediction and molecular generation. However, the standard practice of relying solely on final-layer embeddings for downstream…

Machine Learning · Computer Science 2025-10-16 Luis Pinto

Nobody knows how language works, but many theories abound. Transformers are a class of neural networks that process language automatically with more success than alternatives, both those based on neural computations and those that rely on…

Computation and Language · Computer Science 2024-08-08 Felix Hill

Vision-language models achieve incredible performance across a wide range of tasks, but their large size makes inference costly. Recent work has shown that multimodal processing contains significant redundancies, making it possible to skip…

Artificial Intelligence · Computer Science 2026-05-11 Max Hartman , Vidhata Jayaraman , Moulik Choraria , Akhil Bhimaraju , Lav R. Varshney

Deep networks, composed of multiple layers of hierarchical distributed representations, tend to learn low-level features in initial layers and transition to high-level features towards final layers. Paradigms such as transfer learning,…

Machine Learning · Computer Science 2018-11-30 Haytham M. Fayek , Lawrence Cavedon , Hong Ren Wu

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 whether it is possible to build lighter parsers, that are statistically equivalent to their corresponding standard version, for a wide set of languages showing different structures and morphologies. As testbed, we use the…

Computation and Language · Computer Science 2018-10-23 David Vilares , Carlos Gómez-Rodríguez

Transformers demonstrate impressive performance on a range of reasoning benchmarks. To evaluate the degree to which these abilities are a result of actual reasoning, existing work has focused on developing sophisticated benchmarks for…

Machine Learning · Computer Science 2024-07-02 Jannik Brinkmann , Abhay Sheshadri , Victor Levoso , Paul Swoboda , Christian Bartelt

Analyzing the similarity of internal representations has been an important technique for understanding the behavior of deep neural networks. Most existing methods for analyzing the similarity between representations of high dimensions, such…

Artificial Intelligence · Computer Science 2025-05-26 Jiachen Jiang , Jinxin Zhou , Zhihui Zhu

In the paper we show that there is an analogy between the operations occurring in a layer of a transformer (projections and layer normalizations, disregarding the feedforward neural network) and a step in the power method. Coherently with…

Machine Learning · Computer Science 2026-05-26 Chenglong Li , Claudio Altafini

The Transformer architecture has inarguably revolutionized deep learning, overtaking classical architectures like multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs). At its core, the attention block differs in form and…

Machine Learning · Computer Science 2025-03-18 Weronika Ormaniec , Felix Dangel , Sidak Pal Singh

Multiple studies have shown that Transformers are remarkably robust to pruning. Contrary to this received wisdom, we demonstrate that pre-trained Transformer encoders are surprisingly fragile to the removal of a very small number of…

Computation and Language · Computer Science 2021-06-04 Olga Kovaleva , Saurabh Kulshreshtha , Anna Rogers , Anna Rumshisky

This micro-paper describes a trick to speed up inference of transformers with RoPE (such as LLaMA, Mistral, PaLM, and Gemma). For these models, a large portion of the first transformer layer can be precomputed, which results in slightly…

Machine Learning · Computer Science 2024-03-13 Nils Graef

Alignment training has tradeoffs: it helps language models (LMs) gain in reasoning and instruction following but might lose out on skills such as creativity and calibration, where unaligned base models are better at. We aim to make the best…

Computation and Language · Computer Science 2025-10-14 Shangbin Feng , Wenhao Yu , Yike Wang , Hongming Zhang , Yulia Tsvetkov , Dong Yu

Recent literature suggests that the bigger the model, the more likely it is to converge to similar, ``universal'' representations, despite different training objectives, datasets, or modalities. While this literature shows that there is an…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Matéo Mahaut , Marco Baroni

Graph transformers are a recent advancement in machine learning, offering a new class of neural network models for graph-structured data. The synergy between transformers and graph learning demonstrates strong performance and versatility…

Machine Learning · Computer Science 2025-12-23 Ahsan Shehzad , Feng Xia , Shagufta Abid , Ciyuan Peng , Shuo Yu , Dongyu Zhang , Karin Verspoor