Q Dong, C Cao, Y Fu - … of the IEEE/CVF Conference on …, 2022 - openaccess.thecvf.com
Image inpainting has made significant advances in recent years. However, it is still challenging to recover corrupted images with both vivid textures and reasonable structures …
Adapter-based tuning has recently arisen as an alternative to fine-tuning. It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating the …
Y Xiao, L Wu, J Guo, J Li, M Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Non-autoregressive (NAR) generation, which is first proposed in neural machine translation (NMT) to speed up inference, has attracted much attention in both machine learning and …
Conditional image synthesis aims to create an image according to some multi-modal guidance in the forms of textual descriptions, reference images, and image blocks to …
F Li, J Chen, X Zhang - Electronics, 2023 - mdpi.com
Non-autoregressive neural machine translation (NAMT) has received increasing attention recently in virtue of its promising acceleration paradigm for fast decoding. However, these …
Autoregressive decoding of large language models (LLMs) is memory bandwidth bounded, resulting in high latency and significant wastes of the parallel processing power of modern …
Though nearest neighbor Machine Translation ($ k $ NN-MT)\citep {khandelwal2020nearest } has proved to introduce significant performance boosts over standard neural MT systems, it …
Z Tan, X Zhang, S Wang, Y Liu - arXiv preprint arXiv:2110.06609, 2021 - arxiv.org
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 …
L Yue, Q Liu, Y Du, Y An, L Wang… - Advances in Neural …, 2022 - proceedings.neurips.cc
Rationale extraction can be considered as a straightforward method of improving the model explainability, where rationales are a subsequence of the original inputs, and can be …