English
Related papers

Related papers: Lipschitz Constrained Parameter Initialization for…

200 papers

Transformer networks have become the preferred architecture for many tasks due to their state-of-the-art performance. However, the optimal way to implement residual connections in Transformer, which are essential for effective training, is…

Computation and Language · Computer Science 2023-05-01 Shufang Xie , Huishuai Zhang , Junliang Guo , Xu Tan , Jiang Bian , Hany Hassan Awadalla , Arul Menezes , Tao Qin , Rui Yan

Transformers and large language models~(LLMs) have seen rapid adoption in all domains. Their sizes have exploded to hundreds of billions of parameters and keep increasing. Under these circumstances, the training of transformers is very…

Machine Learning · Computer Science 2026-04-14 Avinash Maurya , Jie Ye , M. Mustafa Rafique , Franck Cappello , Bogdan Nicolae

This paper reveals a novel linear characteristic exclusive to transformer decoders, including models such as GPT, LLaMA, OPT, BLOOM and others. We analyze embedding transformations between sequential layers, uncovering a near-perfect linear…

We present a generalization of Transformers to any-order permutation invariant data (sets, graphs, and hypergraphs). We begin by observing that Transformers generalize DeepSets, or first-order (set-input) permutation invariant MLPs. Then,…

Machine Learning · Computer Science 2022-01-25 Jinwoo Kim , Saeyoon Oh , Seunghoon Hong

The Transformer and its variants have been proven to be efficient sequence learners in many different domains. Despite their staggering success, a critical issue has been the enormous number of parameters that must be trained (ranging from…

Machine Learning · Computer Science 2021-10-28 Subhabrata Dutta , Tanya Gautam , Soumen Chakrabarti , Tanmoy Chakraborty

In this work we consider a generalized bilevel optimization framework for solving inverse problems. We introduce fractional Laplacian as a regularizer to improve the reconstruction quality, and compare it with the total variation…

Image and Video Processing · Electrical Eng. & Systems 2020-06-24 Harbir Antil , Zichao Di , Ratna Khatri

The dominance of large decoder-only language models has overshadowed encoder-decoder architectures, despite their fundamental efficiency advantages in sequence processing. For small language models (SLMs) - those with 1 billion parameters…

Computation and Language · Computer Science 2025-01-31 Mohamed Elfeki , Rui Liu , Chad Voegele

Machine learning is increasingly permeating radio-based localization services. To keep results credible and comparable, everyday workflows should make rigorous experiment specification and exact repeatability the default, without blocking…

Software Engineering · Computer Science 2026-01-22 Tim Strnad , Blaž Bertalanič , Carolina Fortuna

Currently, this paper is under review in IEEE. Transformers have intrigued the vision research community with their state-of-the-art performance in natural language processing. With their superior performance, transformers have found their…

Computer Vision and Pattern Recognition · Computer Science 2022-10-05 Preetam Ghosh , Swalpa Kumar Roy , Bikram Koirala , Behnood Rasti , Paul Scheunders

Recent work explored the potential of large-scale Transformer-based pre-trained models, especially Pre-trained Language Models (PLMs) in natural language processing. This raises many concerns from various perspectives, e.g., financial costs…

Computation and Language · Computer Science 2022-05-23 Yuxin Ren , Benyou Wang , Lifeng Shang , Xin Jiang , Qun Liu

Layer Normalization (LayerNorm) is one of the fundamental components in transformers that stabilizes training and improves optimization. In recent times, Pre-LayerNorm transformers have become the preferred choice over Post-LayerNorm…

Machine Learning · Computer Science 2025-11-14 Rishi Singhal , Jung-Eun Kim

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

Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. However, both the training and inference process of these models may…

Computation and Language · Computer Science 2021-05-04 Jinchuan Tian , Rongzhi Gu , Helin Wang , Yuexian Zou

Large Transformer models yield impressive results on many tasks, but are expensive to train, or even fine-tune, and so slow at decoding that their use and study becomes out of reach. We address this problem by leveraging sparsity. We study…

Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive…

Machine Learning · Computer Science 2024-03-13 Soo Min Kwon , Zekai Zhang , Dogyoon Song , Laura Balzano , Qing Qu

Fine-tuned transformer models have shown superior performances in many natural language tasks. However, the large model size prohibits deploying high-performance transformer models on resource-constrained devices. This paper proposes a…

Computation and Language · Computer Science 2024-10-01 Zi Yang , Samridhi Choudhary , Siegfried Kunzmann , Zheng Zhang

With the rise and ubiquity of larger deep learning models, the need for high-quality compression techniques is growing in order to deploy these models widely. The sheer parameter count of these models makes it difficult to fit them into the…

Computation and Language · Computer Science 2025-04-01 Neha Verma , Kenton Murray , Kevin Duh

In supervised learning, the regularization path is sometimes used as a convenient theoretical proxy for the optimization path of gradient descent initialized from zero. In this paper, we study a modification of the regularization path for…

Machine Learning · Computer Science 2023-08-10 Sebastian Neumayer , Lénaïc Chizat , Michael Unser

Low Rank Decomposition (LRD) is a model compression technique applied to the weight tensors of deep learning models in order to reduce the number of trainable parameters and computational complexity. However, due to high number of new…

Machine Learning · Computer Science 2025-05-27 Habib Hajimolahoseini , Walid Ahmed , Yang Liu

Transformer is a state-of-the-art model in the field of natural language processing (NLP). Current NLP models primarily increase the number of transformers to improve processing performance. However, this technique requires a lot of…

Computation and Language · Computer Science 2023-10-18 Woohyeon Moon , Taeyoung Kim , Bumgeun Park , Dongsoo Har
‹ Prev 1 4 5 6 7 8 10 Next ›