Zobrazeno 1 - 10
of 14 950
pro vyhledávání: '"Dung, P"'
Autor:
Le, Thanh-Dung, Ha, Vu Nguyen, Nguyen, Ti Ti, Eappen, Geoffrey, Thiruvasagam, Prabhu, Chou, Hong-fu, Tran, Duc-Dung, Garces-Socarras, Luis M., Gonzalez-Rios, Jorge L., Merlano-Duncan, Juan Carlos, Chatzinotas, Symeon
This study presents an innovative dynamic weighting knowledge distillation (KD) framework tailored for efficient Earth observation (EO) image classification (IC) in resource-constrained settings. Utilizing EfficientViT and MobileViT as teacher models
Externí odkaz:
http://arxiv.org/abs/2411.00209
Autor:
Chou, Hong-fu, Ha, Vu Nguyen, Thiruvasagam, Prabhu, Le, Thanh-Dung, Eappen, Geoffrey, Nguyen, Ti Ti, Tran, Duc Dung, Garces-Socarras, Luis M., Merlano-Duncan, Juan Carlos, Chatzinotas, Symeon
Earth observation (EO) systems are essential for mapping, catastrophe monitoring, and resource management, but they have trouble processing and sending large amounts of EO data efficiently, especially for specialized applications like agriculture and
Externí odkaz:
http://arxiv.org/abs/2410.21916
Autor:
Le, Cuong Chi, Truong-Vinh, Hoang-Chau, Phan, Huy Nhat, Le, Dung Duy, Nguyen, Tien N., Bui, Nghi D. Q.
Predicting program behavior and reasoning about code execution remain significant challenges in software engineering, particularly for large language models (LLMs) designed for code analysis. While these models excel at understanding static syntax, t
Externí odkaz:
http://arxiv.org/abs/2410.23402
Autor:
Huynh, Minh Tri, Nguyen, Duc Dung
In recent years, motion planning for urban self-driving cars (SDV) has become a popular problem due to its complex interaction of road components. To tackle this, many methods have relied on large-scale, human-sampled data processed through Imitation
Externí odkaz:
http://arxiv.org/abs/2410.22752
Visual Question Answering (VQA) has emerged as a promising area of research to develop AI-based systems for enabling interactive and immersive learning. Numerous VQA datasets have been introduced to facilitate various tasks, such as answering questio
Externí odkaz:
http://arxiv.org/abs/2410.22648
Federated Learning (FL) shows promise in preserving privacy and enabling collaborative learning. However, most current solutions focus on private data collected from a single domain. A significant challenge arises when client data comes from diverse
Externí odkaz:
http://arxiv.org/abs/2410.22622
We conduct the convergence analysis of parameter estimation in the contaminated mixture of experts. This model is motivated from the prompt learning problem where ones utilize prompts, which can be formulated as experts, to fine-tune a large-scaled p
Externí odkaz:
http://arxiv.org/abs/2410.12258
Effective decision-making in partially observable environments demands robust memory management. Despite their success in supervised learning, current deep-learning memory models struggle in reinforcement learning environments that are partially obse
Externí odkaz:
http://arxiv.org/abs/2410.10132
We explore a robust version of the barycenter problem among $n$ centered Gaussian probability measures, termed Semi-Unbalanced Optimal Transport (SUOT)-based Barycenter, wherein the barycenter remains fixed while the others are relaxed using Kullback
Externí odkaz:
http://arxiv.org/abs/2410.08117
Does the choice of programming language affect energy consumption? Previous highly visible studies have established associations between certain programming languages and energy consumption. A causal misinterpretation of this work has led academics a
Externí odkaz:
http://arxiv.org/abs/2410.05460