Výsledky vyhledávání - "Nguyễn Duy Phương"

Akademický článek

Đường bộ qua đèo Hải Vân dưới thời Pháp thuộc (1897 – 1945)

Autor: Nguyễn Duy Phương

Publikováno v: Tạp chí Khoa học và Công nghệ, Pp 51-54 (2024)

Đường đèo Hải Vân dưới thời Pháp thuộc là huyết mạch của con đường thuộc địa số 1 nên được chính quyền thực dân Pháp dành nhiều sự quan tâm cho việc sửa chữa, mở rộng, nâng cấp để p

Externí odkaz: https://doaj.org/article/d0810c6b50f94563b34342fda456b1eb

Zobrazit plný text záznamu

Report

MAGICS: Adversarial RL with Minimax Actors Guided by Implicit Critic Stackelberg for Convergent Neural Synthesis of Robot Safety

Autor: Wang, Justin, Hu, Haimin, Nguyen, Duy Phuong, Fisac, Jaime Fernández

While robust optimal control theory provides a rigorous framework to compute robot control policies that are provably safe, it struggles to scale to high-dimensional problems, leading to increased use of deep learning for tractable synthesis of robot

Externí odkaz: http://arxiv.org/abs/2409.13867

Zobrazit plný text záznamu

Report

FLoRA: Enhancing Vision-Language Models with Parameter-Efficient Federated Learning

Autor: Nguyen, Duy Phuong, Munoz, J. Pablo, Jannesari, Ali

In the rapidly evolving field of artificial intelligence, multimodal models, e.g., integrating vision and language into visual-language models (VLMs), have become pivotal for many applications, ranging from image captioning to multimodal search engin

Externí odkaz: http://arxiv.org/abs/2404.15182

Zobrazit plný text záznamu

Report

ISAACS: Iterative Soft Adversarial Actor-Critic for Safety

Autor: Hsu, Kai-Chieh, Nguyen, Duy Phuong, Fisac, Jaime Fernández

The deployment of robots in uncontrolled environments requires them to operate robustly under previously unseen scenarios, like irregular terrain and wind conditions. Unfortunately, while rigorous safety frameworks from robust optimal control theory

Externí odkaz: http://arxiv.org/abs/2212.03228

Zobrazit plný text záznamu

Report

Enhancing Heterogeneous Federated Learning with Knowledge Extraction and Multi-Model Fusion

Autor: Nguyen, Duy Phuong, Yu, Sixing, Muñoz, J. Pablo, Jannesari, Ali

Concerned with user data privacy, this paper presents a new federated learning (FL) method that trains machine learning models on edge devices without accessing sensitive data. Traditional FL methods, although privacy-protective, fail to manage model

Externí odkaz: http://arxiv.org/abs/2208.07978

Zobrazit plný text záznamu

Report

Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees

Autor: Hsu, Kai-Chieh, Ren, Allen Z., Nguyen, Duy Phuong, Majumdar, Anirudha, Fisac, Jaime F.

Safety is a critical component of autonomous systems and remains a challenge for learning-based policies to be utilized in the real world. In particular, policies learned using reinforcement learning often fail to generalize to novel environments due

Externí odkaz: http://arxiv.org/abs/2201.08355

Zobrazit plný text záznamu