Homepage Of Dr. Hung Le - Home

About

I am Hưng, a senior research lecturer and Australian Research Council DECRA Fellow at Applied Artificial Intelligence Initiative (A2I2), Deakin University.

News

02/2026: 🎉 Our LLM work has been selected for Oral Presentation at Deakin Defence Conference 2026 02/2026: 🎉 My ICLR25 paper has been selected for Oral Presentation at Kingston AI Symposium 2026 01/2026: 🎉 1 paper has been accepted at AISTATS 2026 11/2025: 🎉 1 paper has been accepted at AAAI 2026 11/2025: 👏 I have been promoted to Senior Lecturer position (~ Assoc. Professor in the US) 10/2025: 🎉 1 paper has been accepted at Transactions on Machine Learning Research (J2C certificate) Older

10/2025: 👏 1 of my 2025 PhD scholarships was given to Yafeng Wu 09/2025: 👏 I gave a talk at RemembeRL workshop at CoRL 2025 🔍Hiring 1 Postdoc (Level A, PhD, Junior) – LLM Research: We’re looking for a postdoc to work on large language models (LLMs). If you love Mixture of Experts and can implement ideas from our works, contact me! 09/2025: 👏 I have been invited for an interview by Australian Academy at AI Horizons event 08/2025: 🎉 2 papers have been accepted at ICDM 2025 08/2025: 🎉 1 paper has been accepted at EMNLP 2025 (Findings) 08/2025: 👏 I will give a talk at Sydney AI Meetup 07/2025: 🎉 1 paper has been accepted at ECAI 2025 and another at TMLR journal 06/2025: 👏 I have served as Emergency Area Chair for EMNLP 2025 🔍 Intern Opportunity (Final-Year Undergraduate) – LLM Research: We’re seeking a capable student with strong coding skills and interest in large language models. If you’re comfortable implementing and running experiments with models like these, feel free to reach out. 05/2025: 🎉 1 paper has been accepted at ECML 05/2025: 🎉 1 paper has been accepted at journal Scientific Reports 05/2025: 🎉 1 paper has been accepted at ACL 2025 (Findings) 04/2025: 🎉 2 papers have been accepted at IJCAI 2025 04/2025: 🎉 1 paper has been accepted at International Journal of Impact Engineering journal 03/2025: 🎉 1 paper has been accepted at Transactions on Machine Learning Research and another at Knowledge-Based Systems journals 🔍Hiring 1 Postdoc (Level A, Junior) – LLM Research: We’re looking for a postdoc to work on large language models (LLMs). If you love diving deep into cutting-edge research and can understand and implement ideas from this recent work and this one, contact me! 02/2025: 👏 1 of my 2025 PhD scholarships was given to Hiep Nguyen 02/2025: 🎉 1 paper has been accepted at journal Neural Computing and Applications 02/2025: 👏 I will serve as Area Chair at ACL 2025 02/2025: 🎉 1 paper has been accepted at NAACL 2025 (Industry Track) and another at PAKDD 2025 01/2025: 🎉 2 papers have been accepted at ICLR 2025 and another at NAACL 2025 🔍2025 PhD Student Intake: 1 PhD scholarship available for relevant research topics aligned with my DECRA grant. I am not accepting master's students at this time. Due to the high volume of applications, only shortlisted candidates will receive a response. 12/2024: 💲 Funding Success: Cohere For AI Research Grant 12/2024: 1 paper has been accepted at AAAI 2025 and another at AAMAS 2025 12/2024: My TMLR paper has been invited to present at ICLR 2025 11/2024: I delivered a tutorial on LLM hallucinations at AJCAI 2024 10/2024: 1 paper accepted at WACV 10/2024: My 2024 PhD scholarship was given to Manh Nguyen 09/2024: 1 paper accepted at Transactions on Machine Learning Research journal 09/2024: I have been invited to deliver a tutorial at AJCAI 2024 08/2024: Funding Success: Discovery Early Career Researcher Award (DECRA) 2025 07/2024: 2 papers accepted at ECAI 2024 (Oral) and another at ISSTA 2024 06/2024: I will serve as Senior Program Committee at AAAI 2025 05/2024: 1 paper accepted at ECML-PKDD 2024 2024 Blog: I plan to transfer my blogs to Substack for ease of management 04/2024: 1 paper accepted at IJCAI 2024 02/2024: I will deliver a tutorial at AAMAS 2024. The tutorial will be about exploration in RL. 12/2023: 1 paper accepted at AAMAS 2024 11/2023: 1 paper accepted at Transactions on Machine Learning Research journal 2024 Spring Intake: I am looking for 1 PhD student (full scholarships) who want to work directly with me on neural memory or reinforcement learning topics. Ping me if you find it interesting. 09/2023: 1 paper accepted at ACML 2023 and another at Artificial Intelligence journal 08/2023: I will serve as Senior Program Committee at AAAI 2024 07/2023: My 2023 PhD scholarship was given to Hoang Nguyen and Dai Do 04/2023: 1 paper accepted at IJCAI 2023 and another at International Journal of Impact Engineering 01/2023: 1 paper accepted at ICLR 2023 12/2022: I have delivered AJCAI22 tutorial on Memory-based Reinforcement Learning 11/2022: 1 paper accepted at AAAI 2023 09/2022: 3 papers accepted at NeurIPS 2022 and another 2 at ICONIP 2022 07/2022: I will serve as Senior Program Committee at AAAI 2023 06/2022: 1 paper accepted at ECCV 2022 05/2022: 1 paper accepted at ICML 2022 03/2022: I was promoted to Research Lecturer Position (Permanent Track) 01/2022: 1 paper accepted at NAACL 2022 12/2021: 1 paper accepted at ICLR 2022

Research Focus

Inspired by biological systems and traditional computer architectures, I am deeply passionate about advancing the capacity of neural networks for representational (the what) and functional (the how) learning in computer science. My current research focuses on pioneering advancements in deep learning, reinforcement learning, and artificial memory to develop robust, generalizable and human-like AI solutions for long-term sequence modeling and decision-making. These technologies support diverse applications. My students and I have made significant contributions in the following areas:

1. Robust Neural Networks with Artificial Neural Memory:

• Created novel architectures that incorporate artificial neural memory, leading to breakthroughs in multi-modal and generative AI. ✏️ KDD18, NeurIPS18, ICLR22
• Developed foundational theories for memory mechanisms and emerging capabilities in deep models, enabling more effective learning and reasoning in neural networks. ✏️ ICLR19, ICML20, ICLR23†, ICLR25†
• Investigated the design and implementation of neural computers akin to Universal Turing Machines, capable of handling diverse tasks such as continual learning, machine reasoning and reinforcement learning. ✏️ ICLR20, ICML22
• Devised a general memory module that enhances the generalization and reasoning capabilities of various deep learning models from small RNNs to giant LLMs. ✏️ TMLR24, TMLR25

2. Human-Aligned Artificial Intelligence:

• Developed alignment strategies for LLMs, leveraging collective models or external memories to enhance model generalization and safety. ✏️ AAAI25, ACL25†, EMNLP25†
• Causality-aware models for interpretable decision-making and integrating structural reasoning into deep models. ✏️ IJCAI25†, TMLR25†
• Hallucination and uncertainty estimation for modern AI models such as LLMs. ✏️ AAAI26†

3. Sustainable Autonomous Agents:

• Designed agents that leverage memory to improve decision-making while using less computation. ✏️ NeurIPS21, AAMAS24, ICLR2025
• Developed memory-based optimization approaches to improve sample-efficiency in reinforcement learning. ✏️ NeurIPS22, AAAI22

4. Specialized Data Modeling for Science and Industry

• Pioneered advanced time-series forecasting techniques that support a broad range of scientific and engineering applications. ✏️ ICDM25
• Advanced OCR and document intelligence using machine learning techniques for robust text extraction, layout understanding, and automated information processing. ✏️ TMLR23†

Note: † means student works.

Applications

I have applied these techniques to time-series, dialogue systems, healthcare, human-ai symbiosis, material science, robotics and gaming applications, demonstrating a commitment to advancing AI capabilities across various domains through innovative research and practical applications. The following are some key ongoing projects:

1. Complex Time-series System Forecasting Reinforced by Expert Knowledge

This project leverages LLMs and memory techniques with reinforcement learning to integrate expert knowledge for time-series forecasting. It aims to enhance predictive accuracy in critical areas like healthcare and material science, driving informed decision-making and fostering advancements in forecasting models. This project has been awarded a DECRA25 grant of $428,331 AUD.

2. Obedient Large Language Models (LLMs)

As LLMs rapidly advance, the need for obedient LLMs is urgent—without it, these models can generate outputs that ignore user needs, values, or ethics. LLMs must be designed to listen and follow orders precisely. By incorporating techniques like uncertainty estimation and alignment strategies, LLMs can be trained to reliably follow human instructions, ensuring their outputs align with societal expectations and ethical standards, while reducing risks and ensuring more controlled, effective human-ai symbiosis. This project has secured a valuable seed investment of $10,000 USD through Cohere For AI Research Grant.

Past Research Projects

• Elucidating Human Brain Connectivity Through Deep Learning and Network Analysis (my collobrative project with Deakin’s School of IT, 2021-2023) Project Details
• Memory and Attention in Deep Learning (my PhD at Deakin University, 2017-2020) PhD. Thesis. My great supervisors: A/Prof. Truyen Tran and Prof. Svetha Venkatesh
• Graphical & Topic Model (when I did Master at HUST with A/Prof. Khoat Than, 2016-2017 dropout)
• Kalman Filter & Optimal Control (when I worked at Viettel R&D, 2015-2017)
• Fuzzy Logics (when I did Bachelor Honours at HUST with A/Prof. Khang Tran, 2015)