Zobrazeno 1 - 10
of 20 467
pro vyhledávání: '"ZHAO, Liang"'
Autor:
Huang, Lei, Feng, Xiaocheng, Ma, Weitao, Zhao, Liang, Fan, Yuchun, Zhong, Weihong, Xu, Dongliang, Yang, Qing, Liu, Hongtao, Qin, Bing
Teaching large language models (LLMs) to generate text with citations to evidence sources can mitigate hallucinations and enhance verifiability in information-seeking systems. However, improving this capability requires high-quality attribution data,
Externí odkaz:
http://arxiv.org/abs/2410.13298
In computer-assisted orthopedic surgery (CAOS), accurate pre-operative to intra-operative bone registration is an essential and critical requirement for providing navigational guidance. This registration process is challenging since the intra-operati
Externí odkaz:
http://arxiv.org/abs/2410.03078
Autor:
Hu, Yuntong, Li, Zhuofeng, Zhang, Zheng, Ling, Chen, Kanjiani, Raasikh, Zhao, Boxin, Zhao, Liang
In this work, we present HiReview, a novel framework for hierarchical taxonomy-driven automatic literature review generation. With the exponential growth of academic documents, manual literature reviews have become increasingly labor-intensive and ti
Externí odkaz:
http://arxiv.org/abs/2410.03761
Semantic trajectories, which enrich spatial-temporal data with textual information such as trip purposes or location activities, are key for identifying outlier behaviors critical to healthcare, social security, and urban planning. Traditional outlie
Externí odkaz:
http://arxiv.org/abs/2410.00054
Spiking Neural Networks (SNNs) have recently gained significant interest in on-chip learning in embedded devices and emerged as an energy-efficient alternative to conventional Artificial Neural Networks (ANNs). However, to extend SNNs to a Federated
Externí odkaz:
http://arxiv.org/abs/2409.12769
Few-shot class-incremental learning is crucial for developing scalable and adaptive intelligent systems, as it enables models to acquire new classes with minimal annotated data while safeguarding the previously accumulated knowledge. Nonetheless, exi
Externí odkaz:
http://arxiv.org/abs/2409.11657
Autor:
Batool, Muniba, Azam, Naveed Ahmed, Zhu, Jianshen, Haraguchi, Kazuya, Zhao, Liang, Akutsu, Tatsuya
Aqueous solubility (AS) is a key physiochemical property that plays a crucial role in drug discovery and material design. We report a novel unified approach to predict and infer chemical compounds with the desired AS based on simple deterministic gra
Externí odkaz:
http://arxiv.org/abs/2409.04301
Multiobjective optimization problems (MOPs) are prevalent in machine learning, with applications in multi-task learning, learning under fairness or robustness constraints, etc. Instead of reducing multiple objective functions into a scalar objective,
Externí odkaz:
http://arxiv.org/abs/2409.02969
The three-dimensional vascular model reconstructed from CT images is widely used in medical diagnosis. At different phases, the beating of the heart can cause deformation of vessels, resulting in different vascular imaging states and false positive d
Externí odkaz:
http://arxiv.org/abs/2409.01725
Autor:
Wei, Haoran, Liu, Chenglong, Chen, Jinyue, Wang, Jia, Kong, Lingyu, Xu, Yanming, Ge, Zheng, Zhao, Liang, Sun, Jianjian, Peng, Yuang, Han, Chunrui, Zhang, Xiangyu
Traditional OCR systems (OCR-1.0) are increasingly unable to meet people's usage due to the growing demand for intelligent processing of man-made optical characters. In this paper, we collectively refer to all artificial optical signals (e.g., plain
Externí odkaz:
http://arxiv.org/abs/2409.01704