Zobrazeno 1 - 10
of 91
pro vyhledávání: '"Chen, Jiasi"'
Recent successes in natural language processing have led to the proliferation of large language models (LLMs) by multiple providers. Each LLM offering has different inference accuracy, monetary cost, and latency, and their accuracy further depends on
Externí odkaz:
http://arxiv.org/abs/2404.13082
Modern classification problems exhibit heterogeneities across individual classes: Each class may have unique attributes, such as sample size, label quality, or predictability (easy vs difficult), and variable importance at test-time. Without care, th
Externí odkaz:
http://arxiv.org/abs/2401.14343
Autor:
Slocum, Carter, Zhang, Yicheng, Shayegani, Erfan, Zaree, Pedram, Abu-Ghazaleh, Nael, Chen, Jiasi
Augmented Reality (AR) is expected to become a pervasive component in enabling shared virtual experiences. In order to facilitate collaboration among multiple users, it is crucial for multi-user AR applications to establish a consensus on the "shared
Externí odkaz:
http://arxiv.org/abs/2308.09146
Autor:
Zhang, Xuechen, Li, Mingchen, Chang, Xiangyu, Chen, Jiasi, Roy-Chowdhury, Amit K., Suresh, Ananda Theertha, Oymak, Samet
The growth and diversity of machine learning applications motivate a rethinking of learning with mobile and edge devices. How can we address diverse client goals and learn with scarce heterogeneous data? While federated learning aims to address these
Externí odkaz:
http://arxiv.org/abs/2307.04905
Autor:
Tian, Weihua, Zagami, Chiara, Chen, Jiasi, Blomberg, Anne Louise, Guiu, Laura Salse, Skovbakke, Sarah Line, Goletz, Steffen
Publikováno v:
In New BIOTECHNOLOGY 25 November 2024 83:101-109
Autor:
Yang, Jiaying, Yang, Mei, Wang, Qi, Luo, Qian, Wang, Yingtong, Sun, Jicheng, Liu, Jixuan, Chen, Jiasi, Mao, Juanjuan, Yin, Hailin, Kalvakolanu, Dhan V., Guo, Baofeng, Jiang, Wei, Li, Rui, Zhang, Ling
Publikováno v:
In Chemical Engineering Journal 15 November 2024 500
Imbalanced datasets are commonplace in modern machine learning problems. The presence of under-represented classes or groups with sensitive attributes results in concerns about generalization and fairness. Such concerns are further exacerbated by the
Externí odkaz:
http://arxiv.org/abs/2201.01212
Estimating how well a machine learning model performs during inference is critical in a variety of scenarios (for example, to quantify uncertainty, or to choose from a library of available models). However, the standard accuracy estimate of softmax c
Externí odkaz:
http://arxiv.org/abs/2110.02459
Markerless augmented reality (AR) has the potential to provide engaging experiences and improve outcomes across a wide variety of industries; the overlaying of virtual content, or holograms, onto a view of the real world without the need for predefin
Externí odkaz:
http://arxiv.org/abs/2109.14757
Autor:
Li, Na, Steiger, Stefanie, Zhong, Ming, Lu, Meihua, Lei, Yan, Tang, Chun, Chen, Jiasi, Guo, Yao, Li, Jinhong, Zhang, Dengyang, Li, Jingyi, Zhu, Enyi, Zheng, Zhihua, Lichtnekert, Julia, Chen, Yun, Wang, Xiaohua
Publikováno v:
In Heliyon 15 June 2024 10(11)