Zobrazeno 1 - 10
of 15 984
pro vyhledávání: '"XU Cheng"'
Controlling the style and characteristics of speech synthesis is crucial for adapting the output to specific contexts and user requirements. Previous Text-to-speech (TTS) works have focused primarily on the technical aspects of producing natural-soun
Externí odkaz:
http://arxiv.org/abs/2411.13314
Autor:
Yan, Tianyi, Wu, Dongming, Han, Wencheng, Jiang, Junpeng, Zhou, Xia, Zhan, Kun, Xu, Cheng-zhong, Shen, Jianbing
Autonomous driving evaluation requires simulation environments that closely replicate actual road conditions, including real-world sensory data and responsive feedback loops. However, many existing simulations need to predict waypoints along fixed ro
Externí odkaz:
http://arxiv.org/abs/2411.11252
TSE(Target Speaker Extraction) aims to extract the clean speech of the target speaker in an audio mixture, thus eliminating irrelevant background noise and speech. While prior work has explored various auxiliary cues including pre-recorded speech, vi
Externí odkaz:
http://arxiv.org/abs/2411.03109
Open-vocabulary object detection (OVD) models are considered to be Large Multi-modal Models (LMM), due to their extensive training data and a large number of parameters. Mainstream OVD models prioritize object coarse-grained category rather than focu
Externí odkaz:
http://arxiv.org/abs/2409.16136
Anomaly detection is critical in surveillance systems and patrol robots by identifying anomalous regions in images for early warning. Depending on whether reference data are utilized, anomaly detection can be categorized into anomaly detection with r
Externí odkaz:
http://arxiv.org/abs/2408.12527
Autor:
Xu, Cheng, Zhang, Changtian, Shi, Yuchen, Wang, Ran, Duan, Shihong, Wan, Yadong, Zhang, Xiaotong
Recent advancements in reinforcement learning have made significant impacts across various domains, yet they often struggle in complex multi-agent environments due to issues like algorithm instability, low sampling efficiency, and the challenges of e
Externí odkaz:
http://arxiv.org/abs/2408.11416
Autor:
Wang, An, Sun, Xingwu, Xie, Ruobing, Li, Shuaipeng, Zhu, Jiaqi, Yang, Zhen, Zhao, Pinxue, Han, J. N., Kang, Zhanhui, Wang, Di, Okazaki, Naoaki, Xu, Cheng-zhong
Mixture of Experts (MoE) offers remarkable performance and computational efficiency by selectively activating subsets of model parameters. Traditionally, MoE models use homogeneous experts, each with identical capacity. However, varying complexity in
Externí odkaz:
http://arxiv.org/abs/2408.10681
Autor:
Yang, Haoxin, Xu, Xuemiao, Xu, Cheng, Zhang, Huaidong, Qin, Jing, Wang, Yi, Heng, Pheng-Ann, He, Shengfeng
Reversible face anonymization, unlike traditional face pixelization, seeks to replace sensitive identity information in facial images with synthesized alternatives, preserving privacy without sacrificing image clarity. Traditional methods, such as en
Externí odkaz:
http://arxiv.org/abs/2408.09458
We propose that flat bands and van Hove singularities near the magic angle can be stabilized against angle disorder in the twisted Kane-Mele model. With continuum model and maximally localized Wannier function approaches, we identify a quadratic disp
Externí odkaz:
http://arxiv.org/abs/2408.06866
Autor:
Liu, Genghao, Tang, Baitian, Ren, Liangliang, Li, Chengyuan, Cheng, Sihao, Zong, Weikai, Fu, Jianning, Ma, Bo, Xu, Cheng, Hu, Yiming
Publikováno v:
A&A 690, A29 (2024)
Close white dwarf binaries (CWDBs) are considered to be progenitors of several exotic astronomical phenomena (e.g., type Ia supernovae, cataclysmic variables). These violent events are broadly used in studies of general relativity and cosmology. Howe
Externí odkaz:
http://arxiv.org/abs/2408.03038