English
Related papers

Related papers: Improving Non-autoregressive Generation with Mixup…

200 papers

We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs? We propose mRASP, an approach…

Computation and Language · Computer Science 2021-01-25 Zehui Lin , Xiao Pan , Mingxuan Wang , Xipeng Qiu , Jiangtao Feng , Hao Zhou , Lei Li

Post-training pretrained autoregressive models (ARMs) into masked diffusion models (MDMs) has emerged as a cost-effective way to overcome the limitations of sequential generation. Yet it remains unclear whether post-trained MDMs acquire…

Machine Learning · Computer Science 2026-05-29 Injin Kong , Hyoungjoon Lee , Yohan Jo

Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inherently sequential and unidirectional generation. While…

Computation and Language · Computer Science 2024-08-01 Yuchen Li , Alexandre Kirchmeyer , Aashay Mehta , Yilong Qin , Boris Dadachev , Kishore Papineni , Sanjiv Kumar , Andrej Risteski

Non-autoregressive neural machine translation (NAT) generates each target word in parallel and has achieved promising inference acceleration. However, existing NAT models still have a big gap in translation quality compared to…

Computation and Language · Computer Science 2020-12-17 Qiu Ran , Yankai Lin , Peng Li , Jie Zhou

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

Alignment training has tradeoffs: it helps language models (LMs) gain in reasoning and instruction following but might lose out on skills such as creativity and calibration, where unaligned base models are better at. We aim to make the best…

Computation and Language · Computer Science 2025-10-14 Shangbin Feng , Wenhao Yu , Yike Wang , Hongming Zhang , Yulia Tsvetkov , Dong Yu

Recent studies have demonstrated the importance of high-quality visual representations in image generation and have highlighted the limitations of generative models in image understanding. As a generative paradigm originally designed for…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Xiaoyu Yue , Zidong Wang , Yuqing Wang , Wenlong Zhang , Xihui Liu , Wanli Ouyang , Lei Bai , Luping Zhou

Back-translation is widely known for its effectiveness in neural machine translation when there is little to no parallel data. In this approach, a source-to-target model is coupled with a target-to-source model trained in parallel. The…

Computation and Language · Computer Science 2023-02-14 Wasi Uddin Ahmad , Saikat Chakraborty , Baishakhi Ray , Kai-Wei Chang

This work is on training a generative action/video recognition model whose output is a free-form action-specific caption describing the video (rather than an action class label). A generative approach has practical advantages like producing…

Computer Vision and Pattern Recognition · Computer Science 2022-09-30 Adrian Bulat , Enrique Sanchez , Brais Martinez , Georgios Tzimiropoulos

Likelihood training and maximization-based decoding result in dull and repetitive generated texts even when using powerful language models (Holtzman et al., 2019). Adding a loss function for regularization was shown to improve text…

Computation and Language · Computer Science 2021-01-13 Evgeny Lagutin , Daniil Gavrilov , Pavel Kalaidin

Prompting has recently been shown as a promising approach for applying pre-trained language models to perform downstream tasks. We present Multi-Stage Prompting (MSP), a simple and automatic approach for leveraging pre-trained language…

Computation and Language · Computer Science 2022-03-18 Zhixing Tan , Xiangwen Zhang , Shuo Wang , Yang Liu

Recent text-to-image models produce high-quality results but still struggle with precise visual control, balancing multimodal inputs, and requiring extensive training for complex multimodal image generation. To address these limitations, we…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Haozhe Zhao , Zefan Cai , Shuzheng Si , Liang Chen , Jiuxiang Gu , Wen Xiao , Minjia Zhang , Junjie Hu

How to achieve better end-to-end speech translation (ST) by leveraging (text) machine translation (MT) data? Among various existing techniques, multi-task learning is one of the effective ways to share knowledge between ST and MT in which…

Computation and Language · Computer Science 2023-05-16 Qingkai Fang , Yang Feng

We present RemixIT, a simple yet effective self-supervised method for training speech enhancement without the need of a single isolated in-domain speech nor a noise waveform. Our approach overcomes limitations of previous methods which make…

Sound · Computer Science 2022-08-30 Efthymios Tzinis , Yossi Adi , Vamsi Krishna Ithapu , Buye Xu , Paris Smaragdis , Anurag Kumar

Meta-Learning has emerged as a research direction to better transfer knowledge from related tasks to unseen but related tasks. However, Meta-Learning requires many training tasks to learn representations that transfer well to unseen tasks;…

Computation and Language · Computer Science 2022-10-13 Surya Kant Sahu

While recent neural machine translation approaches have delivered state-of-the-art performance for resource-rich language pairs, they suffer from the data scarcity problem for resource-scarce language pairs. Although this problem can be…

Computation and Language · Computer Science 2017-02-22 Yong Cheng , Yang Liu , Qian Yang , Maosong Sun , Wei Xu

The autoregressive decoding for text generation in large language models (LLMs), while widely used, is inherently suboptimal due to the lack of a built-in mechanism to perform refinement and/or correction of the generated content. In this…

Computation and Language · Computer Science 2025-06-03 Zeyu Tang , Zhenhao Chen , Xiangchen Song , Loka Li , Yunlong Deng , Yifan Shen , Guangyi Chen , Peter Spirtes , Kun Zhang

Autoregressive decoding is the only part of sequence-to-sequence models that prevents them from massive parallelization at inference time. Non-autoregressive models enable the decoder to generate all output symbols independently in…

Computation and Language · Computer Science 2018-11-13 Jindřich Libovický , Jindřich Helcl

In many domains, autoregressive models can attain high likelihood on the task of predicting the next observation. However, this maximum-likelihood (MLE) objective does not necessarily match a downstream use-case of autoregressively…

Machine Learning · Computer Science 2024-05-07 Chris Cundy , Stefano Ermon

Many recent source separation systems are designed to separate a fixed number of sources out of a mixture. In the cases where the source activation patterns are unknown, such systems have to either adjust the number of outputs or to…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-19 Yi Luo , Nima Mesgarani
‹ Prev 1 3 4 5 6 7 10 Next ›