Than Quang Khoat

Associate Professor, Head of the Data Science Lab, Hanoi University of Science and Technology.
Also published as: Thân Quang Khoát, Khoat Than, Quang Khoat Than, Khoat Than Quang, Khoat Quang Than

8 accepted papers at the ten venues since 2020: 7 in the official lists and 1 known only from personal pages, shown as +1 and tagged "unofficial" below. 5 accepted before 2026, 3 from 2026. ICLR: 9 submitted, 3 accepted, 6 rejected. Rejected and on record at other venues (public rejections and papers placed in Findings): NeurIPS 1.

Co-authors

Dung D. Le (VinUni): 1 paper
Ngo Van Linh (HUST): 1 paper

People on this site who share papers with this professor, accepted, rejected or workshop, with their institution today and the number of shared papers; see Researcher collaboration for the whole graph.

Google Scholar

A snapshot of the Google Scholar profile taken on 2026-10-02; it is not updated. Google Scholar counts every publication, not only the ten conferences.

	All	Since 2021
Citations	910	740
h-index	17	17
i10-index	30	26

Citations per year, as shown on Google Scholar on the day of the snapshot.

Submitted and accepted per year

All years: 8 accepted, 7 rejected and on record, and about 7 rejected elsewhere (estimate), so about 22 submissions.

Accepted papers and rejections on record (ICLR, public NeurIPS rejections, Findings) are counted; the light part estimates the rejections the other venues do not publish. The estimate uses this professor's ICLR record: 2.5 submissions per accepted paper (see About). 1 of the accepted papers are known only from personal pages.

Accepted papers per year by where the authors are

Each column is one year's accepted papers; grey papers are known only from announcements or personal pages.

Co-authors and topics

3.8 co-authors per paper on average, accepted or not (fewest on an accepted paper 2, most on any submission 8), 43 different co-authors over 15 papers.
3.2 foreign co-authors per paper on average: co-authors whose affiliation on the paper is outside Vietnam.
31 different co-authors are at another university or institution than HUST (23 abroad, 8 in Vietnam).
The last two figures use the 8 of 15 papers whose list prints an affiliation for each author.
4 topics in 3 areas, from the conference's own label on 4 of 15 papers: General Machine Learning (2), Theory (1), Deep Learning (1).

Topic area	Topic	Papers
Deep Learning	Algorithms	1
General Machine Learning	Representation Learning	1
General Machine Learning	Transfer, Multitask and Meta-learning	1
Theory	Optimization	1

Accepted papers (8)

ICLR 2026 LCA: Local Classifier Alignment for Continual Learning
Tung Tran, Danilo Vasconcellos Vargas, Khoat Than
NeurIPS 2026unofficial Kernelized Activation Steering
Unofficial: name, and listed on their own page; in the NeurIPS 2026 list, not yet confirmable on OpenReview.
Laziz Abdullaev, Minh-Hieu Pham, Bach Do, Khoat Than, Tan Nguyen
CVPR 2026 An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning
Quyen Tran, Hai Nguyen, Quan Dao, Hoang Phan, Linh Van, Khoat Than, Dinh Phung, Dimitris Metaxas, Trung Le
ICLR 2025 Boosting Multiple Views for pretrained-based Continual Learning
Quyen Tran, Tung Lam Tran, Khanh Doan, Toan Tran, Dinh Phung, Khoat Than, Trung Le
ICLR 2025 DPaI: Differentiable Pruning at Initialization with Node-Path Balance Principle
Lichuan Xiang, Quan Nguyen-Tri, Lan-Cuong Nguyen, Hoang Pham, Khoat Than, Long Tran-Thanh, Hongkai Wen
ICML 2025 Provably Improving Generalization of Few-shot models with Synthetic Data
Lan-Cuong Nguyen, Quan Nguyen-Tri, Bang Tran Khanh, Dung D. Le, Long Tran-Thanh, Khoat Than
AAAI 2024 On Inference Stability for Diffusion Models
Viet Nguyen, Giang Vu, Tung Nguyen Thanh, Khoat Than, Toan Tran
ICML 2020 Predictive Coding for Locally-Linear Control
Rui Shu, Tung Nguyen, Yinlam Chow, Tuan Pham, Khoat Than, Mohammad Ghavamzadeh, Stefano Ermon, Hung Bui

Rejected (7)

Submissions that were not accepted.

ICLR 2026, rejected A Non-vacuous Test Error Guarantee for Deep Learning without Altering the Model
Khoat Than, Dat Phan
ICLR 2026, rejected A Tight Error Bound for Deep Learning via Distribution and Loss Complexity
Khoat Than, Vinh Doan, Phuc Le, Phu Phung
ICLR 2026, rejected SUSI: Semi-Structured Pruning for LLMs via Differentiable Subset Sampling
Ha Dinh, Xuan Duy Ta, Khoat Than, Khac-Hoai Nam Bui
NeurIPS 2025, rejected Non-vacuous Bounds for the test error of Deep Learning without any change to the trained models
Khoat Than, Dat Phan
ICLR 2024, rejected Improving Prompt-based Continual Learning with Key-Query Orthogonal Projection and Prototype-based One-Versus-All
Quyen Tran, Tung Lam Tran, Khoat Than, Toan Tran, Dinh Phung, Trung Le
ICLR 2022, rejected Generalization of GANs and overparameterized models under Lipschitz continuity
Khoat Than, Nghia Vu
ICLR 2021, rejected Generalization and Stability of GANs: A theory and promise from data augmentation
Khoat Than, Nghia Vu

Not main track (1)

Datasets & Benchmarks, journal and other tracks, which the site does not count.

NeurIPS 2021 Structured Dropout Variational Inference for Bayesian Neural Networks
Not counted: the paper lists this author at VinAI Research, not at HUST.
Son Nguyen, Duong Nguyen, Khai Nguyen, Khoat Than, Hung Bui, Nhat Ho

Links