Zobrazeno 1 - 10
of 4 324
pro vyhledávání: '"Zhao, Huan"'
We present a pragmatic approach to lower down the mass scale of right-handed neutrinos in leptogenesis by introducing a scalar decaying to right-handed neutrinos. The key point of our proposal is that the out-of-equilibrium decays of the scalar provi
Externí odkaz:
http://arxiv.org/abs/2406.13468
CAD (Computer-Aided Design) plays a crucial role in mechanical industry, where large numbers of similar-shaped CAD parts are often created. Efficiently reusing these parts is key to reducing design and production costs for enterprises. Retrieval syst
Externí odkaz:
http://arxiv.org/abs/2406.08863
Autor:
Ma, Linhan, Guo, Dake, Song, Kun, Jiang, Yuepeng, Wang, Shuai, Xue, Liumeng, Xu, Weiming, Zhao, Huan, Zhang, Binbin, Xie, Lei
With the development of large text-to-speech (TTS) models and scale-up of the training data, state-of-the-art TTS systems have achieved impressive performance. In this paper, we present WenetSpeech4TTS, a multi-domain Mandarin corpus derived from the
Externí odkaz:
http://arxiv.org/abs/2406.05763
Autor:
Gault, Baptiste, Saksena, Aparna, Sauvage, Xavier, Bagot, Paul, Aota, Leonardo S., Arlt, Jonas, Belkacemi, Lisa T., Boll, Torben, Chen, Yi-Sheng, Daly, Luke, Djukic, Milos B., Douglas, James O., Duarte, Maria J., Felfer, Peter J., Forbes, Richard G., Fu, Jing, Gardner, Hazel M., Gemma, Ryota, Gerstl, Stephan S. A., Gong, Yilun, Hachet, Guillaume, Jakob, Severin, Jenkins, Benjamin M., Jones, Megan E., Khanchandani, Heena, Kontis, Paraskevas, Krämer, Mathias, Kühbach, Markus, Marceau, Ross K. W., Mayweg, David, Moore, Katie L., Nallathambi, Varatharaja, Ott, Benedict C., Poplawsky, Jonathan D, Prosa, Ty, Pundt, Astrid, Saha, Mainak, Schwarz, Tim M., Shang, Yuanyuan, Shen, Xiao, Vrellou, Maria, Yu, Yuan, Zhao, Yujun, Zhao, Huan, Zou, Bowen
As hydrogen is touted as a key player in the decarbonization of modern society, it is critical to enable quantitative H analysis at high spatial resolution, if possible at the atomic scale. Indeed, H has a known deleterious impact on the mechanical p
Externí odkaz:
http://arxiv.org/abs/2405.13158
Publikováno v:
published at ICASSP 2024
Conversational Emotion Recognition (CER) aims to predict the emotion expressed by an utterance (referred to as an ``event'') during a conversation. Existing graph-based methods mainly focus on event interactions to comprehend the conversational conte
Externí odkaz:
http://arxiv.org/abs/2405.03960
Publikováno v:
published at ICASSP 2024
Graph representation learning has become a hot research topic due to its powerful nonlinear fitting capability in extracting representative node embeddings. However, for sequential data such as speech signals, most traditional methods merely focus on
Externí odkaz:
http://arxiv.org/abs/2405.03956
Autor:
Cao, Yuji, Zhao, Huan, Cheng, Yuheng, Shu, Ting, Liu, Guolong, Liang, Gaoqi, Zhao, Junhua, Li, Yun
With extensive pre-trained knowledge and high-level general capabilities, large language models (LLMs) emerge as a promising avenue to augment reinforcement learning (RL) in aspects such as multi-task learning, sample efficiency, and task planning. I
Externí odkaz:
http://arxiv.org/abs/2404.00282
Graph-structured data are the commonly used and have wide application scenarios in the real world. For these diverse applications, the vast variety of learning tasks, graph domains, and complex graph learning procedures present challenges for human e
Externí odkaz:
http://arxiv.org/abs/2402.11641
In this study, we present EventRL, a reinforcement learning approach developed to enhance event extraction for large language models (LLMs). EventRL utilizes outcome supervision with specific reward functions to tackle prevalent challenges in LLMs, s
Externí odkaz:
http://arxiv.org/abs/2402.11430
The performance of clients in Federated Learning (FL) can vary due to various reasons. Assessing the contributions of each client is crucial for client selection and compensation. It is challenging because clients often have non-independent and ident
Externí odkaz:
http://arxiv.org/abs/2402.04409