Explanipedia

Single-step hydrothermal synthesis of zinc oxide nanorods for potential use as nano-antibiotics without seeding or bases Open

Chau Nguyen Minh Hoang, Khanh Nguyen, Tinh Luong, Son Hai Nguyen, Mai Thi Tran · 2024

The alarming global rise in antibiotic resistance, driven by the widespread overuse of traditional antibiotics, has created an urgent demand for new antimicrobial solutions. This study presents zinc oxide (ZnO) nanorods as a potential nano…

Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play Open

Sha Li, Revanth Gangi Reddy, Khanh Nguyen, Qingyun Wang, May Fung , et al. · 2024

Complex news events, such as natural disasters and socio-political conflicts, require swift responses from the government and society. Relying on historical events to project the future is insufficient as such events are sparse and do not …

Language-Guided World Models: A Model-Based Approach to AI Control Open

Alex Zhang, Khanh Nguyen, Jens Tuyls, Albert Y. Lin, Karthik Narasimhan · 2024

This paper introduces the concept of Language-Guided World Models (LWMs) -- probabilistic models that can simulate environments by reading texts. Agents equipped with these models provide humans with more extensive and efficient control, a…

RESIN-EDITOR: A Schema-guided Hierarchical Event Graph Visualizer and Editor Open

Khanh Nguyen, Zixuan Zhang, Reece Suchocki, Sha Li, Martha Palmer , et al. · 2023

In this paper, we present RESIN-EDITOR, an interactive event graph visualizer and editor designed for analyzing complex events. Our RESIN-EDITOR system allows users to render and freely edit hierarchical event graphs extracted from multime…

Progressively Efficient Learning Open

Ruijie Zheng, Khanh Nguyen, Hal Daumé, Furong Huang, Karthik Narasimhan · 2023

Assistant AI agents should be capable of rapidly acquiring novel skills and adapting to new user preferences. Traditional frameworks like imitation learning and reinforcement learning do not facilitate this capability because they support …

PopSim: An Individual-level Population Simulator for Equitable Allocation of City Resources Open

Khanh Nguyen, Nima Shahbazi, Abolfazl Asudeh · 2023

Historical systematic exclusionary tactics based on race have forced people of certain demographic groups to congregate in specific urban areas. Aside from the ethical aspects of such segregation, these policies have implications for the a…

RESIN-EDITOR: A Schema-guided Hierarchical Event Graph Visualizer and Editor Open

Khanh Nguyen, Zixuan Zhang, Reece Suchocki, Sha Li, Martha Palmer , et al. · 2023

Khanh Duy Nguyen, Zixuan Zhang, Reece Suchocki, Sha Li, Martha Palmer, Susan Windisch Brown, Jiawei Han, Heng Ji. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 2023.

Improving kernel online learning with a snapshot memory Open

Trung Le, Khanh Nguyen, Dinh Phung · 2022

Nanosers devices based on Au-studded ZnO nanorod for R6G detection Open

Khanh Nguyen, Thu Minh Luong, Khoa Dien Pham, Ngoc Van Le, Thu Thi Hanh Vu , et al. · 2022

Introduction: The prospect of wielding semiconductor–noble metal hybrid nanomaterials as surface-enhanced Raman scattering (SERS) substrates for the ultrasensitive detection of organic molecules in sensing applications has attracted ever-i…

Flexible and Robust Real-Time Intrusion Detection Systems to Network Dynamics Open

Kicho Yu, Khanh Nguyen, Younghee Park · 2022

Deep learning-based intrusion detection systems have advanced due to their technological innovations such as high accuracy, automation, and scalability to develop an effective network intrusion detection system (NIDS). However, most of the…

Learning When and What to Ask: a Hierarchical Reinforcement Learning Framework. Open

Khanh Nguyen, Yonatan Bisk, Hal Daumé · 2021

Reliable AI agents should be mindful of the limits of their knowledge and consult humans when sensing that they do not have sufficient knowledge to make sound decisions. We formulate a hierarchical reinforcement learning framework for lear…

Interactive Learning from Activity Description Open

Khanh Nguyen, Dipendra Misra, Robert E. Schapire, Miro Dudík, Patrick Shafto · 2021

We present a novel interactive learning protocol that enables training request-fulfilling agents by verbally describing their activities. Unlike imitation learning (IL), our protocol allows the teaching agent to provide feedback in a langu…

MirrorNet: Bio-Inspired Adversarial Attack for Camouflaged Object Segmentation Open

Jinnan Yan, Trung-Nghia Le, Khanh Nguyen, Minh–Triet Tran, Thanh-Toan Do , et al. · 2020

Active Imitation Learning from Multiple Non-Deterministic Teachers: Formulation, Challenges, and Algorithms Open

Khanh Nguyen, Hal Daumé · 2020

We formulate the problem of learning to imitate multiple, non-deterministic teachers with minimal interaction cost. Rather than learning a specific policy as in standard imitation learning, the goal in this problem is to learn a distributi…

Code Action Network for Binary Function Scope Identification Open

Van Nguyen, Trung Le, T. Kim Le, Khanh Nguyen, Olivier De Vel , et al. · 2020

Deep Cost-Sensitive Kernel Machine for Binary Software Vulnerability Detection Open

Tuan Nguyen, Trung Le, Khanh Nguyen, Olivier De Vel, Paul Montague , et al. · 2020

Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning Open

Khanh Nguyen, Hal Daumé · 2019

Mobile agents that can leverage help from humans can potentially accomplish more complex tasks than they could entirely on their own. We develop "Help, Anna!" (HANNA), an interactive photo-realistic simulator in which an agent fulfills obj…

Vision-Based Navigation With Language-Based Assistance via Imitation Learning With Indirect Intervention Open

Khanh Nguyen, Debadeepta Dey, Chris Brockett, Bill Dolan · 2019

We present Vision-based Navigation with Language-based Assistance (VNLA), a grounded vision-language task where an agent with visual perception is guided via language to find objects in photorealistic indoor environments. The task emulates…

Global Voices: Crossing Borders in Automatic News Summarization Open

Khanh Nguyen, Hal Daumé · 2019

We construct Global Voices, a multilingual dataset for evaluating cross-lingual summarization methods. We extract social-network descriptions of Global Voices news articles to cheaply collect evaluation data for into-English and from-Engli…

Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning Open

Khanh Nguyen, Hal Daumé · 2019

Khanh Nguyen, Hal Daumé III. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Theoretical Perspective of Deep Domain Adaptation. Open

Trung Le, Khanh Nguyen, Dinh Phung · 2018

On Deep Domain Adaptation: Some Theoretical Understandings Open

Trung Le, Khanh Nguyen, Nhat Ho, Hung Bui, Dinh Phung · 2018

Compared with shallow domain adaptation, recent progress in deep domain adaptation has shown that it can achieve higher predictive performance and stronger capacity to tackle structural data (e.g., image and sequential data). The underlyin…

Clustering Induced Kernel Learning Open

Khanh Nguyen, Nhan Dam, Trung Le, Tu Dinh Nguyen, Dinh Phung · 2018

Essential Properties of Fluorinated Graphene and Graphene Nanoribbons Open

Khanh Nguyen, Thuy Ngoc Thanh Tran, Nguyễn Thành Tiên, Yu-Huang Chiu, Ming‐Fa Lin · 2017

A systematic study is conducted on the fluorination-enriched essential properties of 2D graphene and 1D graphene nanoribbons using the first-principles method. The combined effects, which arise from the significant chemical bonds in C-C, F…

Analogical-based Bayesian Optimization Open

Trung Le, Khanh Nguyen, Tu Dinh Nguyen, Dinh Phung · 2017

Some real-world problems revolve to solve the optimization problem \max_{x\in\mathcal{X}}f\left(x\right) where f\left(.\right) is a black-box function and X might be the set of non-vectorial objects (e.g., distributions) where we can only …

Nonparametric Online Machine Learning with Kernels Open

Khanh Nguyen · 2017

Max-margin and kernel methods are dominant approaches to solve many tasks in machine learning. However, the paramount question is how to solve model selection problem in these methods. It becomes urgent in online learning context. Grid sea…

Inhitive ability collagenase of N-(cinnamyl) chitooligosaccharide derivative Open

Xuan Minh Le, Khanh Nguyen, Khoa D. Tran, Quoc Tuan Tran, Dai‐Nghiep Ngo · 2017

Chitooligosaccharides (COS) with molecular weight 4633 Da and 84.67% of deacetylation were synthesized by hydrolysis of chitosan by cellulase at room temperature (33 ± 1 ° C). This COS, then, were chemically modified by grafting cinnamalde…

Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback Open

Khanh Nguyen, Hal Daumé, Jordan Boyd‐Graber · 2017

Machine translation is a natural candidate problem for reinforcement learning from human feedback: users provide quick, dirty ratings on candidate translations to guide a system to improve. Yet, current neural machine translation training …

The UMD Neural Machine Translation Systems at WMT17 Bandit Learning Task Open

Amr Sharaf, Shi Feng, Khanh Nguyen, Kianté Brantley, Hal Daumé · 2017

We describe the University of Maryland machine translation systems submitted to the WMT17 German-English Bandit Learning Task. The task is to adapt a translation system to a new domain, using only bandit feedback: the system receives a Ger…

Imitation Learning with Recurrent Neural Networks Open

Khanh Nguyen · 2016

We present a novel view that unifies two frameworks that aim to solve sequential prediction problems: learning to search (L2S) and recurrent neural networks (RNN). We point out equivalences between elements of the two frameworks. By comple…

Khanh Nguyen YOU? Author Swipe