Zobrazeno 1 - 10
of 2 327
pro vyhledávání: '"LI, Junhui"'
Previous approaches to the task of implicit discourse relation recognition (IDRR) generally view it as a classification task. Even with pre-trained language models, like BERT and RoBERTa, IDRR still relies on complicated neural networks with multiple
Externí odkaz:
http://arxiv.org/abs/2409.13716
Discrete-modulated continuous-variable quantum key distribution offers a pragmatic solution, greatly simplifying experimental procedures while retaining robust integration with classical optical communication. Theoretical analyses have progressively
Externí odkaz:
http://arxiv.org/abs/2407.20302
Autor:
Li, Junhui, Hou, Xingsong
Deep learning-based methods have garnered significant attention in remote sensing (RS) image compression due to their superior performance. Most of these methods focus on enhancing the coding capability of the compression network and improving entrop
Externí odkaz:
http://arxiv.org/abs/2407.12295
The audio denoising technique has captured widespread attention in the deep neural network field. Recently, the audio denoising problem has been converted into an image generation task, and deep learning-based approaches have been applied to tackle t
Externí odkaz:
http://arxiv.org/abs/2406.09161
Recent diffusion models have achieved promising performances in audio-denoising tasks. The unique property of the reverse process could recover clean signals. However, the distribution of real-world noises does not comply with a single Gaussian distr
Externí odkaz:
http://arxiv.org/abs/2406.09154
Deep learning-based image compression algorithms typically focus on designing encoding and decoding networks and improving the accuracy of entropy model estimation to enhance the rate-distortion (RD) performance. However, few algorithms leverage the
Externí odkaz:
http://arxiv.org/abs/2406.03961
Publikováno v:
The 62nd Annual Meeting of the Association for Computational Linguistics(ACL),2024
In light of recent breakthroughs in large language models (LLMs) that have revolutionized natural language processing (NLP), there is an urgent need for new benchmarks to keep pace with the fast development of LLMs. In this paper, we propose CFLUE, t
Externí odkaz:
http://arxiv.org/abs/2405.10542
Autor:
Li, Junhui, Hou, Xingsong
Decoding remote sensing images to achieve high perceptual quality, particularly at low bitrates, remains a significant challenge. To address this problem, we propose the invertible neural network-based remote sensing image compression (INN-RSIC) meth
Externí odkaz:
http://arxiv.org/abs/2405.10518
Survival regression aims to predict the time when an event of interest will take place, typically a death or a failure. A fully parametric method [18] is proposed to estimate the survival function as a mixture of individual parametric distributions i
Externí odkaz:
http://arxiv.org/abs/2404.15595
Generally, the decoder-only large language models (LLMs) are adapted to context-aware neural machine translation (NMT) in a concatenating way, where LLMs take the concatenation of the source sentence (i.e., intra-sentence context) and the inter-sente
Externí odkaz:
http://arxiv.org/abs/2402.15200