English
Related papers

Related papers: Parameter Sharing Decoder Pair for Auto Composing

200 papers

This paper addresses the challenges of high computational cost and slow inference in deploying large language models. It proposes a distillation strategy guided by multiple teacher models. The method constructs several teacher models and…

Computation and Language · Computer Science 2025-07-22 Xiandong Meng , Yan Wu , Yexin Tian , Xin Hu , Tianze Kang , Junliang Du

Transformer-based pre-trained models have achieved great improvements in semantic matching. However, existing models still suffer from insufficient ability to capture subtle differences. The modification, addition and deletion of words in…

Computation and Language · Computer Science 2023-03-15 Chao Xue , Di Liang , Sirui Wang , Wei Wu , Jing Zhang

Transformer architectures have achieved remarkable success across language, vision, and multimodal tasks, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target…

Machine Learning · Computer Science 2025-11-26 Wei Chen , Jingxi Yu , Zichen Miao , Qiang Qiu

To process novel sentences, language models (LMs) must generalize compositionally -- combine familiar elements in new ways. What aspects of a model's structure promote compositional generalization? Focusing on transformers, we test the…

Computation and Language · Computer Science 2024-04-12 Jackson Petty , Sjoerd van Steenkiste , Ishita Dasgupta , Fei Sha , Dan Garrette , Tal Linzen

We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST). Our models are based on the original Transformer architecture (Vaswani et…

Computation and Language · Computer Science 2020-11-21 Hang Le , Juan Pino , Changhan Wang , Jiatao Gu , Didier Schwab , Laurent Besacier

Multilingual machine translation suffers from negative interference across languages. A common solution is to relax parameter sharing with language-specific modules like adapters. However, adapters of related languages are unable to…

Computation and Language · Computer Science 2022-12-06 Christos Baziotis , Mikel Artetxe , James Cross , Shruti Bhosale

Distributed training of deep neural networks has received significant research interest, and its major approaches include implementations on multiple GPUs and clusters. Parallelization can dramatically improve the efficiency of training…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-11-29 Jaehee Jang , Byungook Na , Sungroh Yoon

Language Model pre-training uses broad data mixtures to enhance performance across domains and languages. However, training on such heterogeneous text corpora requires extensive and expensive efforts. Since these data sources vary…

Machine Learning · Computer Science 2025-04-08 Alex Iacob , Lorenzo Sani , Meghdad Kurmanji , William F. Shen , Xinchi Qiu , Dongqi Cai , Yan Gao , Nicholas D. Lane

In NLP, a large volume of tasks involve pairwise comparison between two sequences (e.g. sentence similarity and paraphrase identification). Predominantly, two formulations are used for sentence-pair tasks: bi-encoders and cross-encoders.…

Computation and Language · Computer Science 2022-03-15 Fangyu Liu , Yunlong Jiao , Jordan Massiah , Emine Yilmaz , Serhii Havrylov

Deep generative models have become increasingly effective at producing realistic images from randomly sampled seeds, but using such models for controllable manipulation of existing images remains challenging. We propose the Swapping…

Computer Vision and Pattern Recognition · Computer Science 2020-12-15 Taesung Park , Jun-Yan Zhu , Oliver Wang , Jingwan Lu , Eli Shechtman , Alexei A. Efros , Richard Zhang

The goal of grammar compression is to construct a small sized context free grammar which uniquely generates the input text data. Among grammar compression methods, RePair is known for its good practical compression performance. MR-RePair…

Data Structures and Algorithms · Computer Science 2019-10-31 Isamu Furuya

Power Delay Profile (PDP) plays a crucial role in wireless communications, providing information on multipath propagation and signal strength variations over time. Accurate detection of peaks within PDP is essential to identify dominant…

Signal Processing · Electrical Eng. & Systems 2026-03-23 Ondrej Zeleny , Radek Zavorka , Ales Prokes , Tomas Fryza , Jaroslaw Wojtun , Jan M. Kelner , Cezary Ziolkowski , Aniruddha Chandra

Supervised training of abstractive language generation models results in learning conditional probabilities over language sequences based on the supervised training signal. When the training signal contains a variety of writing styles, such…

Computation and Language · Computer Science 2018-04-12 Ye Zhang , Nan Ding , Radu Soricut

Neural networks are among the state-of-the-art techniques for language modeling. Existing neural language models typically map discrete words to distributed, dense vector representations. After information processing of the preceding…

Computation and Language · Computer Science 2016-10-14 Yunchuan Chen , Lili Mou , Yan Xu , Ge Li , Zhi Jin

Fine-tuning large pre-trained language models on downstream tasks has become the de-facto learning paradigm in NLP. However, conventional approaches fine-tune all the parameters of the pre-trained model, which becomes prohibitive as the…

Computation and Language · Computer Science 2022-02-03 Junxian He , Chunting Zhou , Xuezhe Ma , Taylor Berg-Kirkpatrick , Graham Neubig

Systems for synthesizer sound matching, which automatically set the parameters of a synthesizer to emulate an input sound, have the potential to make the process of synthesizer programming faster and easier for novice and experienced…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-24 Fred Bruford , Frederik Blang , Shahan Nercessian

Tensor decomposition is an important technique for capturing the high-order interactions among multiway data. Multi-linear tensor composition methods, such as the Tucker decomposition and the CANDECOMP/PARAFAC (CP), assume that the complex…

Machine Learning · Statistics 2016-11-04 Bin Liu , Zenglin Xu , Yingming Li

In this paper we propose an efficient deep learning encoder-decoder network for performing Harmonic-Percussive Source Separation (HPSS). It is shown that we are able to greatly reduce the number of model trainable parameters by using a…

Sound · Computer Science 2019-07-31 Carlos Lordelo , Emmanouil Benetos , Simon Dixon , Sven Ahlbäck

We introduce SPAFormer, an innovative model designed to overcome the combinatorial explosion challenge in the 3D Part Assembly (3D-PA) task. This task requires accurate prediction of each part's poses in sequential steps. As the number of…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Boshen Xu , Sipeng Zheng , Qin Jin

Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternative approach in which…

Computation and Language · Computer Science 2025-05-06 Henry Ndubuaku , Mouad Talhi