Dung D. Le

Assistant Professor, Director, Data Science Program, VinUniversity. At a Vietnamese institution since 2021.
Also published as: Lê Duy Dũng, Dung Duy Le, Duy Dung Le, Dung Le

11 accepted papers at the ten venues since 2021: 8 in the official lists and 3 known only from personal pages, shown as +3 and tagged "unofficial" below. 6 accepted before 2026, 5 from 2026. ICLR: 9 submitted, 1 accepted, 8 rejected. Rejected and on record at other venues (public rejections and papers placed in Findings): CVPR 1, ACL 1.

Links

1. Homepage: andrew-dungle.github.io
2. OpenReview profile (~Dung_D._Le2): openreview.net/profile?id=~Dung_D._Le2
3. Staff page: vinuni.edu.vn/people/le-duy-dung
4. DBLP: dblp.org/pid/186/1477
5. Google Scholar: scholar.google.com/citations?user=0eoYR1gAAAAJ

Co-authors

1. Than Quang Khoat (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.

Submitted and accepted per year

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

• 4.1 co-authors per paper on average, accepted or not (fewest on an accepted paper 2, most on any submission 7), 62 different co-authors over 21 papers.
• 2.1 foreign co-authors per paper on average: co-authors whose affiliation on the paper is outside Vietnam.
• 32 different co-authors are at another university or institution than VinUni (18 abroad, 14 in Vietnam).
• The last two figures use the 9 of 21 papers whose list prints an affiliation for each author.
• 2 topics in 2 areas, from the conference's own label on 3 of 21 papers: Deep Learning (2), General Machine Learning (1).

Accepted papers (11)

• ICLR 2026 CLIP-FMoE: Scalable CLIP via Fused Mixture-of-Experts with Enforced Specialization
  Luong Tran, Lan-Cuong Nguyen, Huynh Dang Nguyen, Dat Nguyen Cong, Dung D. Le, Van Nguyen
• NeurIPS 2026unofficial Latent Abstraction for Retrieval-Augmented Generation
  Unofficial: listed on their own page; not in the official list yet.
  Dung D. Le, Ha Lan T. Nguyen, Nguyen Anh Minh
• NeurIPS 2026unofficial MulCLIP: A Multi-level Alignment Framework for Enhancing Fine-grained Long-context CLIP
  Unofficial: name, and listed on their own page; in the NeurIPS 2026 list, not yet confirmable on OpenReview.
  Chau T Hoang, Hieu Ta, Zhenzhen Liu, Dung Le
• NeurIPS 2026unofficial Trajectory-Matching Meta Pseudo-Labeling for Semi-Supervised Learning
  Unofficial: listed on their own page; not in the official list yet.
  Dung D. Le, Duc Le Minh, Minh-Duong Nguyen
• CVPR 2026 Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict Mitigation and Expression
  Minh-Duong Nguyen, Senura Wanasekara, Le-Tuan Nguyen, Quoc-Viet Pham, Ken-Tye Yong, Nguyen H. Tran, Dung D. Le
• 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 2025 Improving Pareto Set Learning for Expensive Multi-objective Optimization via Stein Variational Hypernetworks
  Minh-Duc Nguyen, Phuong Mai Dinh, Quang-Huy Nguyen, Long P. Hoang, Dung D. Le
• NeurIPS 2023 Towards Data-Agnostic Pruning At Initialization: What Makes a Good Sparse Mask?
  Hoang Pham, The-Anh Ta, Shiwei Liu, Lichuan Xiang, Dung D. Le, Hongkai Wen, Long Tran-Thanh
• EMNLP 2023 Reinforced Target-driven Conversational Promotion
  Huy Quang Dao, Lizi Liao, Dung D. Le, Yuxiang Nie
• AAAI 2023 Improving Pareto Front Learning via Multi-Sample Hypernetworks
  Long P. Hoang, Dung D. Le, Tran Anh Tuan, Tran Ngoc Thang
• ICML 2022spotlight Improving Transformers with Probabilistic Attention Keys
  Tam Nguyen, Tan Nguyen, Dung Le, Duy Khuong Nguyen, Viet-Anh Tran, Richard Baraniuk, Nhat Ho, Stanley Osher

Rejected (10)

Submissions that were not accepted.

• ICLR 2026, rejected Exploiting Client Heterogeneity for Forgetting Mitigation in Federated Continual Learning: A Spatio-Temporal Gradient Alignment Approach
  Duong Minh Nguyen, Le-Tuan Nguyen, Dung D. Le, Quoc-Viet Pham
• ICLR 2026, rejected FLoRA-NA: Nearly Accurate Aggregation for Federated Low-Rank Adaptation
  Le-Tuan Nguyen, Duong Minh Nguyen, Seon-Geun Jeong, Dung D. Le, Quoc-Viet Pham
• ICLR 2026, rejected MulCLIP: A Multi-level Alignment Framework for Enhancing Fine-grained Long-context CLIP
  The same title was accepted at NeurIPS 2026.
  Chau Truong Vinh Hoang, HIEU TA QUANG, Dung D. Le
• ICLR 2026, rejected SyNC: Balancing Fidelity and Diversity of Synthetic Data Representations in CLIP-based Few-Shot Learning via Neural Collapse
  Thanh Duc Pham, Lan-Cuong Nguyen, Dung D. Le, Minh-Tan Pham
• CVPR 2026 · Findings, rejected Memory-Efficient Continual Learning with Prototypical Exemplar Condensation
  M.-Duong Nguyen, Thien-Thanh Dao, Le-Tuan Nguyen, Dung D. Le, Kok-Seng Wong
• ICLR 2025, rejected VisualCoder: Guiding Vision Language Models in Code Execution with Fine-grained Chain-of-Thought Reasoning
  Cuong Chi Le, Chau Truong Vinh Hoang, Phan Nhật Huy, Dung D. Le, Tien N Nguyen, Nghi D. Q. Bui
• ICLR 2025, rejected Zero-shot Object-level Out-of-distribution Detection with Context-aware Inpainting
  Quang-Huy Nguyen, Jin Peng Zhou, Zhenzhen Liu, Khanh-Huyen Bui, Kilian Q Weinberger, Wei-Lun Chao, Dung D. Le
• ACL 2024, rejectedunofficial A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models
  Unofficial: listed on their own page; not in the official list yet.
  Dung D. Le, Dang Cao Cuong, Thai Le
• ICLR 2023, rejected Understanding Pruning at Initialization: An Effective Node-Path Balancing Perspective
  Hoang Pham, Anh Ta, Shiwei Liu, Dung D. Le, Long Tran-Thanh
• ICLR 2022, rejected Transformer with a Mixture of Gaussian Keys
  Tam Minh Nguyen, Tan Minh Nguyen, Dung Duy Le, Nguyen Duy Khuong, Viet Anh TRAN, Richard Baraniuk, Nhat Ho, Stanley Osher

Not main track (2)

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

• NeurIPS 2026unofficial Benchmarking Vietnamese Legal Knowledge of Large Language Models
  Not counted: Datasets & Benchmarks track.
  Unofficial: name, and listed on their own page; in the NeurIPS 2026 list, not yet confirmable on OpenReview.
  Dong N Tien, Nguyen Minh-Anh, Thanh D Hoang, Nguyen T Ngoc, Quang M Xuan, Phan P Hai, Nguyen T Anh, Binh Vu, Dung Le
• NeurIPS 2026unofficial HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning
  Not counted: Datasets & Benchmarks track.
  Unofficial: name, and listed on their own page; in the NeurIPS 2026 list, not yet confirmable on OpenReview.
  Thinh Nguyen, Le-Tuan Nguyen, Minh-Duong Nguyen, Nhi Trinh, Anh T Nguyet, Dung Le, Kok-Seng Wong

Workshop papers (4)

Workshop papers found on OpenReview and papers placed in Findings, for reference; not counted, except that a Findings paper counts as a main-track rejection (see About).

• ICML 2026 · workshop AI4Science A Multi-Agent LLM Framework with Hierarchical Citation Graph for Automated Survey Generation
  Nguyen Anh Minh, Minh Duc Nguyen, Ha Lan T. Nguyen, Hai Dang Kieu, Dong Nguyen Tien, Dung D. Le
• CVPR 2026 · Findings Memory-Efficient Continual Learning with Prototypical Exemplar Condensation
  M.-Duong Nguyen, Thien-Thanh Dao, Le-Tuan Nguyen, Dung D. Le, Kok-Seng Wong
• ACL 2024 · Findingsunofficial A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models
  Unofficial: listed on their own page; not in the official list yet.
  Dung D. Le, Dang Cao Cuong, Thai Le
• ICLR 2022 · workshop GTRL Learning Weighted Product Spaces Representations for Graphs of Heterogeneous Structures
  Tuc Van Nguyen, Dung D. Le, Anh Ta