English
Related papers

Related papers: Fast Interleaved Bidirectional Sequence Generation

200 papers

Neural translation models have proven to be effective in capturing sufficient information from a source sentence and generating a high-quality target sentence. However, it is not easy to get the best effect for bidirectional translation,…

Computation and Language · Computer Science 2020-11-25 Parnia Bahar , Christopher Brix , Hermann Ney

Neural end-to-end TTS can generate very high-quality synthesized speech, and even close to human recording within similar domain text. However, it performs unsatisfactory when scaling it to challenging test sets. One concern is that the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-07-23 Yibin Zheng , Xi Wang , Lei He , Shifeng Pan , Frank K. Soong , Zhengqi Wen , Jianhua Tao

The use of deep pre-trained bidirectional transformers has led to remarkable progress in a number of applications (Devlin et al., 2018). For tasks that make pairwise comparisons between sequences, matching a given input with a corresponding…

Computation and Language · Computer Science 2020-03-27 Samuel Humeau , Kurt Shuster , Marie-Anne Lachaux , Jason Weston

Inference from large autoregressive models like Transformers is slow - decoding K tokens takes K serial runs of the model. In this work we introduce speculative decoding - an algorithm to sample from autoregressive models faster without any…

Machine Learning · Computer Science 2023-05-22 Yaniv Leviathan , Matan Kalman , Yossi Matias

Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass.…

Computation and Language · Computer Science 2025-06-12 Nadav Timor , Jonathan Mamou , Daniel Korat , Moshe Berchansky , Gaurav Jain , Oren Pereg , Moshe Wasserblat , David Harel

Despite the remarkable strides made by autoregressive language models, their potential is often hampered by the slow inference speeds inherent in sequential token generation. Blockwise parallel decoding (BPD) was proposed by Stern et al. as…

Computation and Language · Computer Science 2024-06-06 Taehyeon Kim , Ananda Theertha Suresh , Kishore Papineni , Michael Riley , Sanjiv Kumar , Adrian Benton

Due to the highly parallelizable architecture, Transformer is faster to train than RNN-based models and popularly used in machine translation tasks. However, at inference time, each output word requires all the hidden states of the…

Computation and Language · Computer Science 2019-09-06 Chengyi Wang , Shuangzhi Wu , Shujie Liu

Autoregressive generation is a powerful approach for high-fidelity image synthesis, but it remains computationally demanding and slow even on the most advanced accelerators. While speculative decoding has been explored to mitigate this…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Selin Yildirim , Subhajit Dutta Chowdhury , Mohammad Mahdi Kamani , Vikram Appia , Deming Chen

The encoder-decoder model is widely used in natural language generation tasks. However, the model sometimes suffers from repeated redundant generation, misses important phrases, and includes irrelevant entities. Toward solving these…

Computation and Language · Computer Science 2017-12-25 Shun Kiyono , Sho Takase , Jun Suzuki , Naoaki Okazaki , Kentaro Inui , Masaaki Nagata

The dominant approach to sequence generation is to produce a sequence in some predefined order, e.g. left to right. In contrast, we propose a more general model that can generate the output sequence by inserting tokens in any arbitrary…

Computation and Language · Computer Science 2019-11-04 Dmitrii Emelianenko , Elena Voita , Pavel Serdyukov

Sequence-to-sequence learning naturally has two directions. How to effectively utilize supervision signals from both directions? Existing approaches either require two separate models, or a multitask-learned model but with inferior…

Computation and Language · Computer Science 2022-01-25 Zaixiang Zheng , Hao Zhou , Shujian Huang , Jiajun Chen , Jingjing Xu , Lei Li

Simultaneous translation, which starts translating each sentence after receiving only a few words in source sentence, has a vital role in many scenarios. Although the previous prefix-to-prefix framework is considered suitable for…

Computation and Language · Computer Science 2022-01-03 Zhengxin Yang

Simultaneous machine translation consists in starting output generation before the entire input sequence is available. Wait-k decoders offer a simple but efficient approach for this problem. They first read k source tokens, after which they…

Computation and Language · Computer Science 2020-08-05 Maha Elbayad , Laurent Besacier , Jakob Verbeek

The recent emergence of Large Language Models based on the Transformer architecture has enabled dramatic advancements in the field of Natural Language Processing. However, these models have long inference latency, which limits their…

Computation and Language · Computer Science 2023-10-13 Sehoon Kim , Karttikeya Mangalam , Suhong Moon , Jitendra Malik , Michael W. Mahoney , Amir Gholami , Kurt Keutzer

Recent advances in image and video generation have raised significant interest from both academia and industry. A key challenge in this field is improving inference efficiency, as model size and the number of inference steps directly impact…

Computer Vision and Pattern Recognition · Computer Science 2025-10-15 Victor Besnier , David Hurych , Andrei Bursuc , Eduardo Valle

We investigate methods to reduce inference time and memory footprint in stable diffusion models by introducing lightweight decoders for both image and video synthesis. Traditional latent diffusion pipelines rely on large Variational…

Computer Vision and Pattern Recognition · Computer Science 2025-03-10 Alexey Buzovkin , Evgeny Shilov

Diffusion large language models (dLLMs) generate text through iterative denoising. In commonly adopted parallel decoding schemes, each step confirms only high-confidence positions while remasking the others. By analyzing dLLM denoising…

Computation and Language · Computer Science 2026-05-27 Kangyu Wang , Zhiyun Jiang , Haibo Feng , Weijia Zhao , Lin Liu , Jianguo Li , Zhenzhong Lan , Weiyao Lin

Large language models (LLMs) exhibit exceptional performance across a wide range of tasks; however, their token-by-token autoregressive generation process significantly hinders inference speed. Speculative decoding presents a promising…

Computation and Language · Computer Science 2025-03-04 Kai Lv , Honglin Guo , Qipeng Guo , Xipeng Qiu

The dominant neural machine translation (NMT) models apply unified attentional encoder-decoder neural networks for translation. Traditionally, the NMT decoders adopt recurrent neural networks (RNNs) to perform translation in a left-toright…

Computation and Language · Computer Science 2018-02-06 Xiangwen Zhang , Jinsong Su , Yue Qin , Yang Liu , Rongrong Ji , Hongji Wang

In this paper, we propose a simple, fast decoding algorithm that fosters diversity in neural generation. The algorithm modifies the standard beam search algorithm by adding an inter-sibling ranking penalty, favoring choosing hypotheses from…

Computation and Language · Computer Science 2016-12-23 Jiwei Li , Will Monroe , Dan Jurafsky