English
Related papers

Related papers: On Sparsifying Encoder Outputs in Sequence-to-Sequ…

200 papers

LLMs used for code generation are typically guided by engineering constraints--technology choices, dependency restrictions, and architectural patterns--expressed in verbose natural language. We investigate whether compact, structured…

Software Engineering · Computer Science 2026-04-23 Hanzhang Tang

As large language models continue to scale, their growing computational and storage demands pose significant challenges for real-world deployment. In this work, we investigate redundancy within Transformer-based models and propose an…

Computation and Language · Computer Science 2025-04-08 Liangwei Yang , Yuhui Xu , Juntao Tan , Doyen Sahoo , Silvio Savarese , Caiming Xiong , Huan Wang , Shelby Heinecke

Transformer-based neural speech processing has achieved state-of-the-art performance. Since speech audio signals are known to be highly compressible, here we seek to accelerate neural speech transcription by time-domain signal…

Machine Learning · Computer Science 2025-06-23 Zifei Xu , Sayeh Sharify , Hesham Mostafa , Tristan Webb , Wanzin Yazar , Xin Wang

Transformer networks have seen great success in natural language processing and machine vision, where task objectives such as next word prediction and image classification benefit from nuanced context sensitivity across high-dimensional…

Machine Learning · Computer Science 2022-12-13 Yuxuan Li , James L. McClelland

Large Language Models (LLMs) have demonstrated remarkable proficiency in language comprehension and generation; however, their widespread adoption is constrained by substantial bandwidth and computational demands. While pruning and low-rank…

Computation and Language · Computer Science 2025-10-31 Zeliang Zong , Kai Zhang , Zheyang Li , Wenming Tan , Ye Ren , Yiyan Zhai , Jilin Hu

Massively pre-trained transformer models are computationally expensive to fine-tune, slow for inference, and have large storage requirements. Recent approaches tackle these shortcomings by training smaller models, dynamically reducing the…

Machine Learning · Computer Science 2021-10-07 Andreas Rücklé , Gregor Geigle , Max Glockner , Tilman Beck , Jonas Pfeiffer , Nils Reimers , Iryna Gurevych

Transformer-based models are unable to process long sequences due to their self-attention operation, which scales quadratically with the sequence length. To address this limitation, we introduce the Longformer with an attention mechanism…

Computation and Language · Computer Science 2020-12-03 Iz Beltagy , Matthew E. Peters , Arman Cohan

Model merging has emerged as a compelling data-free paradigm for multi-task learning, enabling the fusion of multiple fine-tuned models into a single, powerful entity. A key technique in merging methods is sparsification, which prunes…

Computation and Language · Computer Science 2025-08-11 Yingfeng Luo , Dingyang Lin , Junxin Wang , Ziqiang Xu , Kaiyan Chang , Tong Zheng , Bei Li , Anxiang Ma , Tong Xiao , Zhengtao Yu , Jingbo Zhu

This paper proposes serialized output training (SOT), a novel framework for multi-speaker overlapped speech recognition based on an attention-based encoder-decoder approach. Instead of having multiple output layers as with the permutation…

Computation and Language · Computer Science 2020-08-11 Naoyuki Kanda , Yashesh Gaur , Xiaofei Wang , Zhong Meng , Takuya Yoshioka

Sparse neural networks are often hypothesized to be more interpretable than dense models, motivated by findings that weight sparsity can produce compact circuits in language models. However, it remains unclear whether structural sparsity…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Siyu Zhang

Label smoothing is a regularization technique for neural networks. Normally neural models are trained to an output distribution that is a vector with a single 1 for the correct prediction, and 0 for all other elements. Label smoothing…

Software Engineering · Computer Science 2023-03-29 Sakib Haque , Aakash Bansal , Collin McMillan

Increasing the input length has been a driver of progress in language modeling with transformers. We identify conditions where shorter inputs are not harmful, and achieve perplexity and efficiency improvements through two new methods that…

Computation and Language · Computer Science 2021-06-04 Ofir Press , Noah A. Smith , Mike Lewis

Transformer-based language models are applied to a wide range of applications in natural language processing. However, they are inefficient and difficult to deploy. In recent years, many compression algorithms have been proposed to increase…

Computation and Language · Computer Science 2021-11-11 Ofir Zafrir , Ariel Larey , Guy Boudoukh , Haihao Shen , Moshe Wasserblat

We rigorously evaluate three state-of-the-art techniques for inducing sparsity in deep neural networks on two large-scale learning tasks: Transformer trained on WMT 2014 English-to-German, and ResNet-50 trained on ImageNet. Across thousands…

Machine Learning · Computer Science 2019-02-27 Trevor Gale , Erich Elsen , Sara Hooker

Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models for language modeling, yet the effective design of transformer architectures for MDMs remains underexplored. In this paper, we show that…

Machine Learning · Computer Science 2026-05-26 Sanghyun Lee , Chunsan Hong , Seungryong Kim , Jonghyun Lee , Jongho Park , Dongmin Park

A good neural sequence-to-sequence summarization model should have a strong encoder that can distill and memorize the important information from long input texts so that the decoder can generate salient summaries based on the encoder's…

Computation and Language · Computer Science 2018-09-13 Yichen Jiang , Mohit Bansal

In this letter, we propose a sparsification method for precoding codebooks that reduces the peak-to-average power ratio (PAPR) while preserving the achievable rate. By exploiting the fact that precoder matrices lie on the Grassmann…

Signal Processing · Electrical Eng. & Systems 2026-04-22 Joe Asano , Yuto Hama , Hiroki Iimori , Szabolcs Malomsoky , Naoki Ishikawa

Tokenization is a fundamental component of language models for code. It involves breaking down the input into units that are later passed to the language model stack to learn high-dimensional representations used in various contexts, from…

Software Engineering · Computer Science 2025-07-22 Mootez Saad , Hao Li , Tushar Sharma , Ahmed E. Hassan

Reasoning language models such as DeepSeek-R1 produce long chain-of-thought traces during inference time which make them costly to deploy at scale. We show that using compression techniques such as neural network pruning produces greater…

Artificial Intelligence · Computer Science 2026-05-05 Ryan Lucas , Kayhan Behdin , Zhipeng Wang , Qingquan Song , Shao Tang , Rahul Mazumder

Many natural language generation tasks, such as abstractive summarization and text simplification, are paraphrase-orientated. In these tasks, copying and rewriting are two main writing modes. Most previous sequence-to-sequence (Seq2Seq)…

Computation and Language · Computer Science 2016-11-29 Ziqiang Cao , Chuwei Luo , Wenjie Li , Sujian Li
‹ Prev 1 8 9 10 Next ›