Thang Doan

Thang Doan

McGill University

H-index: 12

North America-Canada

About Thang Doan

Thang Doan, With an exceptional h-index of 12 and a recent h-index of 12 (since 2020), a distinguished researcher at McGill University, specializes in the field of reinforcement learning, multimodal, lifelong learning, vision language model, Open World.

His recent articles reflect a diverse array of research interests and contributions to the field:

Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection

A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets

GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients

UP-DP: Unsupervised Prompt Learning for Data Pre-Selection with Vision-Language Models

Building a Subspace of Policies for Scalable Continual Learning

Continual Learning Beyond a Single Model

Low-Rank Representation of Reinforcement Learning Policies

Method and system for generating aspects associated with a future event for a subject

Thang Doan Information

University

Position

Mila /

Citations(all)

618

Citations(since 2020)

612

Cited By

114

hIndex(all)

12

hIndex(since 2020)

12

i10Index(all)

14

i10Index(since 2020)

14

Email

University Profile Page

Google Scholar

Thang Doan Skills & Research Interests

reinforcement learning

multimodal

lifelong learning

vision language model

Open World

Top articles of Thang Doan

Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection

2024

A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets

arXiv preprint arXiv:2403.06295

2024/3/10

GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients

NeurIPS 2023

2023

UP-DP: Unsupervised Prompt Learning for Data Pre-Selection with Vision-Language Models

NeurIPS 2023

2023

Building a Subspace of Policies for Scalable Continual Learning

ICLR 2023

2022/11/18

Continual Learning Beyond a Single Model

2023

Thang Doan
Thang Doan

H-Index: 7

Seyed Iman Mirzadeh
Seyed Iman Mirzadeh

H-Index: 4

Low-Rank Representation of Reinforcement Learning Policies

Journal of Artificial Intelligence Research

2022/10/27

Method and system for generating aspects associated with a future event for a subject

2021/4/29

Domain Adversarial Reinforcement Learning

Deep RL workshop Neurips 2020

2021/2/14

Uncertainty quantification in skin cancer classification using three-way decision-based Bayesian deep learning

Computers in biology and medicine

2021/4/28

A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix

2021

Regularized Inverse Reinforcement Learning

arXiv preprint arXiv:2010.03691

2020/10/7

Generalisation guarantees for continual learning with orthogonal gradient descent

ICML workshop on Lifelong Learning 2020

2020/6/21

Thang Doan
Thang Doan

H-Index: 7

Deep Reinforcement and InfoMax Learning

2020

Bogdan Mazoure
Bogdan Mazoure

H-Index: 6

Thang Doan
Thang Doan

H-Index: 7

See List of Professors in Thang Doan University(McGill University)

Co-Authors

academic-engine