English
Related papers

Related papers: Efficient Monotonic Multihead Attention

200 papers

Modern large language models become multimodal, analyzing various data formats like text and images. While fine-tuning is effective for adapting these multimodal language models (MLMs) to downstream tasks, full fine-tuning is…

Computation and Language · Computer Science 2025-12-01 Alexander Sergeev , Evgeny Kotelnikov

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated satisfactory performance across various vision-language tasks. Current approaches for vision and language interaction fall into two categories:…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Feipeng Ma , Yizhou Zhou , Zheyu Zhang , Shilin Yan , Hebei Li , Zilong He , Siying Wu , Fengyun Rao , Yueyi Zhang , Xiaoyan Sun

Various natural language processing (NLP) tasks necessitate models that are efficient and small based on their ultimate application at the edge or in other resource-constrained environments. While prior research has reduced the size of…

Computation and Language · Computer Science 2023-06-27 Victor Agostinelli , Lizhong Chen

Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as…

Computation and Language · Computer Science 2022-05-17 Gerard Sant , Gerard I. Gállego , Belen Alastruey , Marta R. Costa-Jussà

Computational workloads composing traditional transformer models are starkly bifurcated. Multi-Head Attention (MHA) and Grouped-Query Attention are memory-bound due to low arithmetic intensity, while FeedForward Networks are compute-bound.…

Recent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate as-yet-unarrived words, when dealing with a language pair…

Computation and Language · Computer Science 2021-10-20 HyoJung Han , Seokchan Ahn , Yoonjung Choi , Insoo Chung , Sangha Kim , Kyunghyun Cho

We propose Hymba, a family of small language models featuring a hybrid-head parallel architecture that integrates transformer attention mechanisms with state space models (SSMs) for enhanced efficiency. Attention heads provide…

Entity-aware machine translation (EAMT) is a complicated task in natural language processing due to not only the shortage of translation data related to the entities needed to translate but also the complexity in the context needed to…

Computation and Language · Computer Science 2025-06-24 An Trieu , Phuong Nguyen , Minh Le Nguyen

An attentional mechanism has lately been used to improve neural machine translation (NMT) by selectively focusing on parts of the source sentence during translation. However, there has been little work exploring useful architectures for…

Computation and Language · Computer Science 2015-09-22 Minh-Thang Luong , Hieu Pham , Christopher D. Manning

Emotion represents an essential aspect of human speech that is manifested in speech prosody. Speech, visual, and textual cues are complementary in human communication. In this paper, we study a hybrid fusion method, referred to as…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-10 Zexu Pan , Zhaojie Luo , Jichen Yang , Haizhou Li

Simultaneous speech translation (SimulST) produces translations incrementally while processing partial speech input. Although large language models (LLMs) have showcased strong capabilities in offline translation tasks, applying them to…

Computation and Language · Computer Science 2025-04-17 Biao Fu , Donglei Yu , Minpeng Liao , Chengxi Li , Yidong Chen , Kai Fan , Xiaodong Shi

Self-attention mechanism has been widely used for various tasks. It is designed to compute the representation of each position by a weighted sum of the features at all positions. Thus, it can capture long-range relations for computer vision…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Xia Li , Zhisheng Zhong , Jianlong Wu , Yibo Yang , Zhouchen Lin , Hong Liu

In this paper, we improve the attention or alignment accuracy of neural machine translation by utilizing the alignments of training sentence pairs. We simply compute the distance between the machine attentions and the "true" alignments, and…

Computation and Language · Computer Science 2016-08-02 Haitao Mi , Zhiguo Wang , Abe Ittycheriah

Machine Translation (MT) is a zone of concentrate in Natural Language processing which manages the programmed interpretation of human language, starting with one language then onto the next by the PC. Having a rich research history…

Computation and Language · Computer Science 2019-09-24 Siddhant Srivastava , Ritu Tiwari

Mamba-based architectures have shown to be a promising new direction for deep learning models owing to their competitive performance and sub-quadratic deployment speed. However, current Mamba multi-modal large language models (MLLM) are…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Yifei Xing , Xiangyuan Lan , Ruiping Wang , Dongmei Jiang , Wenjun Huang , Qingfang Zheng , Yaowei Wang

Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation outputs. The great…

Computation and Language · Computer Science 2021-08-13 Zi-Yi Dou , Graham Neubig

Text-only adaptation of an end-to-end (E2E) model remains a challenging task for automatic speech recognition (ASR). Language model (LM) fusion-based approaches require an additional external LM during inference, significantly increasing…

Computation and Language · Computer Science 2022-11-01 Zhong Meng , Yashesh Gaur , Naoyuki Kanda , Jinyu Li , Xie Chen , Yu Wu , Yifan Gong

We present MoE-MLA-RoPE, a novel architecture combination that combines Mixture of Experts (MoE) with Multi-head Latent Attention (MLA) and Rotary Position Embeddings (RoPE) for efficient language modeling. Our approach addresses the…

Artificial Intelligence · Computer Science 2025-08-05 Sushant Mehta , Raj Dandekar , Rajat Dandekar , Sreedath Panat

Emergency Medical Services (EMS) responders often operate under time-sensitive conditions, facing cognitive overload and inherent risks, requiring essential skills in critical thinking and rapid decision-making. This paper presents…

Artificial Intelligence · Computer Science 2024-10-27 Keshara Weerasinghe , Saahith Janapati , Xueren Ge , Sion Kim , Sneha Iyer , John A. Stankovic , Homa Alemzadeh

Training large foundation models using self-supervised objectives on unlabeled data, followed by fine-tuning on downstream tasks, has emerged as a standard procedure. Unfortunately, the efficacy of this approach is often constrained by both…