Zobrazeno 1 - 10
of 628 284
pro vyhledávání: '"Yong, P"'
Circumstellar OH maser lines are useful for studying the dynamics of the circumstellar envelope (CSE) around evolved stars. This study aims to identify CSEs around cold stars bf, which exhibit deviations from the spherical expansion, by comparing the
Externí odkaz:
http://arxiv.org/abs/2411.08399
Diffusion-based text-to-audio (TTA) generation has made substantial progress, leveraging latent diffusion model (LDM) to produce high-quality, diverse and instruction-relevant audios. However, beyond generation, the task of audio editing remains equa
Externí odkaz:
http://arxiv.org/abs/2409.12466
Autor:
Zhou, Jiaming, Zhao, Shiwan, He, Jiabei, Wang, Hui, Zeng, Wenjia, Chen, Yong, Sun, Haoqin, Kong, Aobo, Qin, Yong
State-of-the-art models like OpenAI's Whisper exhibit strong performance in multilingual automatic speech recognition (ASR), but they still face challenges in accurately recognizing diverse subdialects. In this paper, we propose M2R-whisper, a novel
Externí odkaz:
http://arxiv.org/abs/2409.11889
Autor:
Yin, Rui, Qin, Haotong, Zhang, Yulun, Li, Wenbo, Guo, Yong, Zhu, Jianjun, Wang, Cheng, Jia, Biao
Dense prediction is a critical task in computer vision. However, previous methods often require extensive computational resources, which hinders their real-world application. In this paper, we propose BiDense, a generalized binary neural network (BNN
Externí odkaz:
http://arxiv.org/abs/2411.10346
Autor:
Yuan, Zixiong, Yue, Wen-Cheng, Huang, Peiyuan, Lyu, Yang-Yang, Dong, Sining, Dong, Ying, Wang, Huabing, Wu, Peiheng, Wang, Yong-Lei
Publikováno v:
Physical Review B 110, 174422 (2024)
Artificial spin ices provide a controlled platform for investigating diverse physical phenomena, such as geometric frustration, magnetic monopoles, and phase transitions, via deliberate design. Here, we introduce a novel approach by developing artifi
Externí odkaz:
http://arxiv.org/abs/2411.10264
Medical images often exhibit distribution shifts due to variations in imaging protocols and scanners across different medical centers. Domain Generalization (DG) methods aim to train models on source domains that can generalize to unseen target domai
Externí odkaz:
http://arxiv.org/abs/2411.10136
Autor:
Li, Pengfei, Liu, Ang, Kluge, Matthias, Comparat, Johan, Tian, Yong, Júlio, Mariana P., Pawlowski, Marcel S., Sanders, Jeremy, Bulbul, Esra, Schwope, Axel, Ghirardini, Vittorio, Zhang, Xiaoyuan, Bahar, Y. Emre, Ramos-Ceja, Miriam E., Balzer, Fabian, Garrel, Christian
The mass of galaxy clusters is a critical quantity for probing cluster cosmology and testing theories of gravity, but its measurement could be biased given assumptions are inevitable. In this paper, we employ and compare two mass proxies for galaxy c
Externí odkaz:
http://arxiv.org/abs/2411.09735
Inferring object motion representations from observations enhances the performance of robotic manipulation tasks. This paper introduces a new paradigm for robot imitation learning that generates action sequences by reasoning about object motion from
Externí odkaz:
http://arxiv.org/abs/2411.09658
Autor:
Gan, Yuyou, Yang, Yong, Ma, Zhe, He, Ping, Zeng, Rui, Wang, Yiming, Li, Qingming, Zhou, Chunyi, Li, Songze, Wang, Ting, Gao, Yunjun, Wu, Yingcai, Ji, Shouling
With the continuous development of large language models (LLMs), transformer-based models have made groundbreaking advances in numerous natural language processing (NLP) tasks, leading to the emergence of a series of agents that use LLMs as their con
Externí odkaz:
http://arxiv.org/abs/2411.09523
Pre-training plays a vital role in various vision tasks, such as object recognition and detection. Commonly used pre-training methods, which typically rely on randomized approaches like uniform or Gaussian distributions to initialize model parameters
Externí odkaz:
http://arxiv.org/abs/2411.09453