English
Related papers

Related papers: Transformer Feed-Forward Layers Are Key-Value Memo…

200 papers

Feed-forward neural networks consist of a sequence of layers, in which each layer performs some processing on the information from the previous layer. A downside to this approach is that each layer (or module, as multiple modules can…

Machine Learning · Computer Science 2020-10-19 Alex Lamb , Anirudh Goyal , Agnieszka Słowik , Michael Mozer , Philippe Beaudoin , Yoshua Bengio

We conduct a systematic study of the approximation properties of Transformer for sequence modeling with long, sparse and complicated memory. We investigate the mechanisms through which different components of Transformer, such as the…

Machine Learning · Computer Science 2024-10-31 Mingze Wang , Weinan E

We seek to understand how the representations of individual tokens and the structure of the learned feature space evolve between layers in deep neural networks under different learning objectives. We focus on the Transformers for our…

Computation and Language · Computer Science 2019-09-05 Elena Voita , Rico Sennrich , Ivan Titov

Recurrent neural network architectures can have useful computational properties, with complex temporal dynamics and input-sensitive attractor states. However, evaluation of recurrent dynamic architectures requires solution of systems of…

Neural and Evolutionary Computing · Computer Science 2019-11-18 Dylan Richard Muir

This paper investigates the key role of Feed-Forward Networks (FFNs) in transformer models by utilizing the Parallel Attention and Feed-Forward Net Design (PAF) architecture, and comparing it to their Series Attention and Feed-Forward Net…

Computation and Language · Computer Science 2023-05-26 Shashank Sonkar , Richard G. Baraniuk

Large language models based on transformers have achieved great empirical successes. However, as they are deployed more widely, there is a growing need to better understand their internal mechanisms in order to make them more reliable.…

Machine Learning · Statistics 2023-11-08 Alberto Bietti , Vivien Cabannes , Diane Bouchacourt , Herve Jegou , Leon Bottou

Language Models (LMs) have shown their application for tasks pertinent to code and several code~LMs have been proposed recently. The majority of the studies in this direction only focus on the improvements in performance of the LMs on…

Artificial Intelligence · Computer Science 2024-07-09 Muhammad Umair Haider , Umar Farooq , A. B. Siddique , Mark Marron

Semantic associations such as the link between "bird" and "flew" are foundational for language modeling as they enable models to go beyond memorization and instead generalize and generate coherent text. Understanding how these associations…

Computation and Language · Computer Science 2026-05-14 Shawn Im , Changdae Oh , Zhen Fang , Sharon Li

Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…

Machine Learning · Computer Science 2021-02-26 Yujing Wang , Yaming Yang , Jiangang Bai , Mingliang Zhang , Jing Bai , Jing Yu , Ce Zhang , Gao Huang , Yunhai Tong

This work presents an analysis of the effectiveness of using standard shallow feed-forward networks to mimic the behavior of the attention mechanism in the original Transformer model, a state-of-the-art architecture for sequence-to-sequence…

Computation and Language · Computer Science 2024-02-06 Vukasin Bozic , Danilo Dordevic , Daniele Coppola , Joseph Thommes , Sidak Pal Singh

In recent years, the impact of self-supervised speech Transformers has extended to speaker-related applications. However, little research has explored how these models encode speaker information. In this work, we address this gap by…

Computation and Language · Computer Science 2025-06-30 Tzu-Quan Lin , Hsi-Chun Cheng , Hung-yi Lee , Hao Tang

Next to scaling considerations, architectural design choices profoundly shape the solution space of transformers. In this work, we analyze the solutions simple transformer blocks implement when tackling the histogram task: counting items in…

Machine Learning · Computer Science 2025-11-13 Freya Behrens , Luca Biggio , Lenka Zdeborová

There have been significant efforts to interpret the encoder of Transformer-based encoder-decoder architectures for neural machine translation (NMT); meanwhile, the decoder remains largely unexamined despite its critical role. During…

Computation and Language · Computer Science 2020-10-07 Yilin Yang , Longyue Wang , Shuming Shi , Prasad Tadepalli , Stefan Lee , Zhaopeng Tu

We investigate multi-scale transformer language models that learn representations of text at multiple scales, and present three different architectures that have an inductive bias to handle the hierarchical nature of language. Experiments…

Computation and Language · Computer Science 2020-05-05 Sandeep Subramanian , Ronan Collobert , Marc'Aurelio Ranzato , Y-Lan Boureau

Although it is known that transformer language models (LMs) pass features from early layers to later layers, it is not well understood how this information is represented and routed by the model. We analyze a mechanism used in two LMs to…

Computation and Language · Computer Science 2025-05-12 Jack Merullo , Carsten Eickhoff , Ellie Pavlick

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

Despite their nearly universal adoption for large language models, the internal workings of transformers are not well understood. We aim to better understand the impact of removing or reorganizing information throughout the layers of a…

Computation and Language · Computer Science 2025-02-14 Qi Sun , Marc Pickett , Aakash Kumar Nain , Llion Jones

Prompt tuning is an emerging way of adapting pre-trained language models to downstream tasks. However, the existing studies are mainly to add prompts to the input sequence. This way would not work as expected due to the intermediate…

Computation and Language · Computer Science 2022-07-01 Jingping Liu , Yuqiu Song , Kui Xue , Hongli Sun , Chao Wang , Lihan Chen , Haiyun Jiang , Jiaqing Liang , Tong Ruan

We show that small and shallow feed-forward neural networks can achieve near state-of-the-art results on a range of unstructured and structured language processing tasks while being considerably cheaper in memory and computational…

Computation and Language · Computer Science 2017-08-02 Jan A. Botha , Emily Pitler , Ji Ma , Anton Bakalov , Alex Salcianu , David Weiss , Ryan McDonald , Slav Petrov

Matching animal-like flexibility in recognition and the ability to quickly incorporate new information remains difficult. Limits are yet to be adequately addressed in neural models and recognition algorithms. This work proposes a…

Computer Vision and Pattern Recognition · Computer Science 2012-06-26 Tsvi Achler