English
Related papers

Related papers: Birth of a Transformer: A Memory Viewpoint

200 papers

Some Transformer-based models can perform cross-lingual transfer learning: those models can be trained on a specific task in one language and give relatively good results on the same task in another language, despite having been pre-trained…

Computation and Language · Computer Science 2022-07-20 Félix Gaschi , François Plesse , Parisa Rastin , Yannick Toussaint

Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference. We study the impact of model size in this setting,…

Computation and Language · Computer Science 2020-06-24 Zhuohan Li , Eric Wallace , Sheng Shen , Kevin Lin , Kurt Keutzer , Dan Klein , Joseph E. Gonzalez

Interactive speech recognition systems must generate words quickly while also producing accurate results. Two-pass models excel at these requirements by employing a first-pass decoder that quickly emits words, and a second-pass decoder that…

Computation and Language · Computer Science 2021-01-28 Ke Hu , Ruoming Pang , Tara N. Sainath , Trevor Strohman

To produce accurate predictions, language models (LMs) must balance between generalization and memorization. Yet, little is known about the mechanism by which transformer LMs employ their memorization capacity. When does a model decide to…

Computation and Language · Computer Science 2023-02-14 Adi Haviv , Ido Cohen , Jacob Gidron , Roei Schuster , Yoav Goldberg , Mor Geva

The transformer architecture and variants presented remarkable success across many machine learning tasks in recent years. This success is intrinsically related to the capability of handling long sequences and the presence of…

Machine Learning · Computer Science 2022-06-15 Luckeciano C. Melo

We identify incremental learning dynamics in transformers, where the difference between trained and initial weights progressively increases in rank. We rigorously prove this occurs under the simplifying assumptions of diagonal weight…

Machine Learning · Computer Science 2023-12-12 Enric Boix-Adsera , Etai Littwin , Emmanuel Abbe , Samy Bengio , Joshua Susskind

Large-scale models for learning fixed-dimensional cross-lingual sentence representations like LASER (Artetxe and Schwenk, 2019b) lead to significant improvement in performance on downstream tasks. However, further increases and…

Computation and Language · Computer Science 2022-05-30 Zhuoyuan Mao , Prakhar Gupta , Pei Wang , Chenhui Chu , Martin Jaggi , Sadao Kurohashi

The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including mathematical reasoning, memorization, and retrieval - using…

Machine Learning · Computer Science 2025-09-05 Yihe Dong , Lorenzo Noci , Mikhail Khodak , Mufan Li

Language modeling has shown us that transformers can discover latent structure from context, but the dynamics of how they acquire different components of that structure remain poorly understood, leading to assertions that models just remix…

Machine Learning · Computer Science 2026-04-23 Rohan Saha , Farzane Aminmansour , Alona Fyshe

Transformer-based pre-trained models have gained much advance in recent years, becoming one of the most important backbones in natural language processing. Recent work shows that the attention mechanism inside Transformer may not be…

Computation and Language · Computer Science 2022-10-27 Yile Wang , Linyi Yang , Zhiyang Teng , Ming Zhou , Yue Zhang

The Outstanding performance and growing size of Large Language Models has led to increased attention in parameter efficient learning. The two predominant approaches are Adapters and Pruning. Adapters are to freeze the model and give it a…

Computation and Language · Computer Science 2023-04-07 Guorun Wang , Jun Yang , Yaoru Sun

Pre-trained language models demonstrate general intelligence and common sense, but long inputs quickly become a bottleneck for memorizing information at inference time. We resurface a simple method, Memorizing Transformers (Wu et al.,…

Machine Learning · Computer Science 2024-06-05 Phoebe Klett , Thomas Ahle

Large Transformer models have achieved impressive performance in many natural language tasks. In particular, Transformer based language models have been shown to have great capabilities in encoding factual knowledge in their vast amount of…

Computation and Language · Computer Science 2020-12-02 Chen Zhu , Ankit Singh Rawat , Manzil Zaheer , Srinadh Bhojanapalli , Daliang Li , Felix Yu , Sanjiv Kumar

The relationship between memorization and generalization in large language models (LLMs) remains an open area of research, with growing evidence that the two are deeply intertwined. In this work, we investigate this relationship by…

Machine Learning · Computer Science 2025-06-19 Joshua Barron , Devin White

Learning arguably involves the discovery and memorization of abstract rules. The aim of this paper is to study associative memory mechanisms. Our model is based on high-dimensional matrices consisting of outer products of embeddings, which…

Machine Learning · Statistics 2024-02-22 Vivien Cabannes , Elvis Dohmatob , Alberto Bietti

A growing body of research has demonstrated that the behavior of large language models can be effectively controlled at inference time by directly modifying their internal states, either through vector additions to their activations or…

Machine Learning · Computer Science 2026-02-06 Hanna Mazzawi , Benoit Dherin , Michael Munn , Michael Wunder , Javier Gonzalvo

Large language models have consistently struggled with complex reasoning tasks, such as mathematical problem-solving. Investigating the internal reasoning mechanisms of these models can help us design better model architectures and training…

Artificial Intelligence · Computer Science 2025-09-10 Zhiwei Wang , Yunji Wang , Zhongwang Zhang , Zhangchen Zhou , Hui Jin , Tianyang Hu , Jiacheng Sun , Zhenguo Li , Yaoyu Zhang , Zhi-Qin John Xu

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

Transformers have recently been utilized to perform object detection and tracking in the context of autonomous driving. One unique characteristic of these models is that attention weights are computed in each forward pass, giving insights…

Computer Vision and Pattern Recognition · Computer Science 2022-10-27 Felicia Ruppel , Florian Faion , Claudius Gläser , Klaus Dietmayer

Trained transformer models have been found to implement interpretable procedures for tasks like arithmetic and associative recall, but little is understood about how the circuits that implement these procedures originate during training. To…

Machine Learning · Computer Science 2024-10-08 Ziqian Zhong , Jacob Andreas