English
Related papers

Related papers: Accelerating Transformer Inference for Translation…

200 papers

Recent neural network models for image captioning usually employ an encoder-decoder architecture, where the decoder adopts a recursive sequence decoding way. However, such autoregressive decoding may result in sequential error accumulation…

Computer Vision and Pattern Recognition · Computer Science 2019-12-16 Zheng-cong Fei

Diffusion models are powerful generative models but suffer from slow sampling, often taking 1000 sequential denoising steps for one sample. As a result, considerable efforts have been directed toward reducing the number of denoising steps,…

Machine Learning · Computer Science 2023-10-17 Andy Shih , Suneel Belkhale , Stefano Ermon , Dorsa Sadigh , Nima Anari

Automatic parallelization remains a challenging problem in software engineering, particularly in identifying code regions where loops can be safely executed in parallel on modern multi-core architectures. Traditional static analysis…

Software Engineering · Computer Science 2026-04-01 Izavan dos S. Correia , Henrique C. T. Santos , Tiago A. E. Ferreira

Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-18 Jingwei Song , Wanyi Chen , Xinyuan Song , Max , Chris Tong , Gufeng Chen , Tianyi Zhao , Eric Yang , Bill Shi , Lynn Ai

Efficient large-scale inference of transformer-based large language models (LLMs) remains a fundamental systems challenge, frequently requiring multi-GPU parallelism to meet stringent latency and throughput targets. Conventional tensor…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-10 Chong Wang , Nan Du , Tom Gunter , Tao Lei , Kulin Seth , Senyu Tong , Jianyu Wang , Guoli Yin , Xiyou Zhou , Kelvin Zou , Ruoming Pang

Non-Autoregressive machine Translation (NAT) models have demonstrated significant inference speedup but suffer from inferior translation accuracy. The common practice to tackle the problem is transferring the Autoregressive machine…

Computation and Language · Computer Science 2021-05-18 Yongchang Hao , Shilin He , Wenxiang Jiao , Zhaopeng Tu , Michael Lyu , Xing Wang

Handwriting recognition is a challenging and critical problem in the fields of pattern recognition and machine learning, with applications spanning a wide range of domains. In this paper, we focus on the specific issue of recognizing…

Computer Vision and Pattern Recognition · Computer Science 2023-07-28 Saleh Momeni , Bagher BabaAli

Large language model (LLM) decoding involves generating a sequence of tokens based on a given context, where each token is predicted one at a time using the model's learned probabilities. The typical autoregressive decoding method requires…

Computation and Language · Computer Science 2024-08-20 Xukun Liu , Bowen Lei , Ruqi Zhang , Dongkuan Xu

Non-autoregressive Transformers (NATs) reduce the inference latency of Autoregressive Transformers (ATs) by predicting words all at once rather than in sequential order. They have achieved remarkable progress in machine translation as well…

Computation and Language · Computer Science 2023-06-05 Chenxin An , Jiangtao Feng , Fei Huang , Xipeng Qiu , Lingpeng Kong

Attention-based autoregressive models have achieved state-of-the-art performance in various sequence-to-sequence tasks, including Text-To-Speech (TTS) and Neural Machine Translation (NMT), but can be difficult to train. The standard…

Computation and Language · Computer Science 2022-11-08 Qingyun Dou , Mark Gales

In this work, we propose FastCoT, a model-agnostic framework based on parallel decoding without any further training of an auxiliary model or modification to the LLM itself. FastCoT uses a size-varying context window whose size changes with…

Computation and Language · Computer Science 2024-06-05 Hongxuan Zhang , Zhining Liu , Yao Zhao , Jiaqi Zheng , Chenyi Zhuang , Jinjie Gu , Guihai Chen

We aim to better exploit the limited amounts of parallel text available in low-resource settings by introducing a differentiable reconstruction loss for neural machine translation (NMT). This loss compares original inputs to reconstructed…

Computation and Language · Computer Science 2019-04-05 Xing Niu , Weijia Xu , Marine Carpuat

In this work, we introduce a novel local autoregressive translation (LAT) mechanism into non-autoregressive translation (NAT) models so as to capture local dependencies among tar-get outputs. Specifically, for each target decoding position,…

Computation and Language · Computer Science 2020-11-13 Xiang Kong , Zhisong Zhang , Eduard Hovy

In Neural Machine Translation (NMT), the decoder can capture the features of the entire prediction history with neural connections and representations. This means that partial hypotheses with different prefixes will be regarded differently…

Computation and Language · Computer Science 2018-10-16 Zhisong Zhang , Rui Wang , Masao Utiyama , Eiichiro Sumita , Hai Zhao

Recently, the Transformer model that is based solely on attention mechanisms, has advanced the state-of-the-art on various machine translation tasks. However, recent studies reveal that the lack of recurrence hinders its further improvement…

Computation and Language · Computer Science 2019-04-08 Jie Hao , Xing Wang , Baosong Yang , Longyue Wang , Jinfeng Zhang , Zhaopeng Tu

Speculative decoding, which combines a draft model with a target model, has emerged as an effective approach to accelerate large language model (LLM) inference. However, existing methods often face a trade-off between the acceptance rate…

Computation and Language · Computer Science 2025-05-14 Danying Ge , Jianhua Gao , Qizhi Jiang , Yifei Feng , Weixing Ji

The recently proposed mask-predict decoding algorithm has narrowed the performance gap between semi-autoregressive machine translation models and the traditional left-to-right approach. We introduce a new training method for conditional…

Computation and Language · Computer Science 2020-01-27 Marjan Ghazvininejad , Omer Levy , Luke Zettlemoyer

Modern machine translation (MT) systems depend on large parallel corpora, often collected from the Internet. However, recent evidence indicates that (i) a substantial portion of these texts are machine-generated translations, and (ii) an…

Computation and Language · Computer Science 2025-11-06 Cristian García-Romero , Miquel Esplà-Gomis , Felipe Sánchez-Martínez

Diffusion transformers have demonstrated remarkable generation quality, albeit requiring longer training iterations and numerous inference steps. In each denoising step, diffusion transformers encode the noisy inputs to extract the…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Shuai Wang , Zhi Tian , Weilin Huang , Limin Wang

Non-autoregressive neural machine translation (NAT) predicts the entire target sequence simultaneously and significantly accelerates inference process. However, NAT discards the dependency information in a sentence, and thus inevitably…

Computation and Language · Computer Science 2020-06-11 Qiu Ran , Yankai Lin , Peng Li , Jie Zhou