Variational Inference (VI) first starts as a handy tool in Bayesian inference to approximate intractable posterior. Now, its usage goes beyond Bayesian inference, and we can see VI everywhere in classic learning, and deep learning-anywhere needs an approximation. After this lecture, we should: Read more

preprints

Memory-Augmented Neural Networks for Predictive Process Analytics

Published: March 02, 2019

Authors: Asjad Khan*, Hung Le*, Kien Do, Truyen Tran, Aditya Ghose, Hoa Dam, Renuka Sindhgatta.
Link

Improving Long Handwritten Text Line Recognition with Convolutional Multi-way Associative Memory

Published: November 05, 2019

Authors: Duc Nguyen, Nhan Tran, Hung Le.
Link

Plug and Play, Model-Based Reinforcement Learning

Published: August 20, 2021

Authors: Majid Abdolshah, Hung Le, Thommen Karimpanal George, Sunil Gupta, Santu Rana, Svetha Venkatesh.
Link

publications

Dual Control Memory Augmented Neural Networks for Treatment Recommendations

Published/Accepted at PAKDD, 2018

Authors: Hung Le, Truyen Tran, Svetha Venkatesh
Code•PDF•Link

Dual Memory Neural Computer for Asynchronous Two-view Sequential Learning

Published/Accepted at KDD, 2018

Authors: Hung Le, Truyen Tran, Svetha Venkatesh
Code•Poster•PDF•Link

Variational Memory Encoder-Decoder

Published/Accepted at NeurIPS, 2018

Authors: Hung Le, Truyen Tran, Thin Nguyen, Svetha Venkatesh
Code•Poster•PDF•Link

Learning to Remember More with Less Memorization

Published/Accepted at ICLR (Oral), 2019

Authors: Hung Le, Truyen Tran, Svetha Venkatesh
Code•Poster•Blog•PDF•Link

Neural Stored-Program Memory

Published/Accepted at ICLR, 2020

Authors: Hung Le, Truyen Tran, Svetha Venkatesh
Code•Talk•Slides•PDF•Link

LODENet: A Holistic Approach to Offline Handwritten Chinese and Japanese Text Line Recognition

Published/Accepted at ICPR, 2020

Authors: Huu Tin Hoang, Chun-Jen Peng, Hung Tran, Hung Le, Huy Hoang Nguyen.
Link

Self-attentive Associative Memory

Published/Accepted at ICML, 2020

Authors: Hung Le, Truyen Tran, Svetha Venkatesh
Code•Talk•Slides•PDF•Link

A New Representation of Successor Features for Transfer across Dissimilar Environments

Published/Accepted at ICML (Spotlight), 2021

Authors: Majid Abdolshah, Hung Le, Thommen George Karimpanal, Sunil Gupta, Santu Rana, Svetha Venkatesh.
Link

DeepProcess: Supporting Business Process Execution Using a MANN-based Recommender System

Published/Accepted at ICSOC, 2021

Authors: Asjad Khan, Aditya Ghose, Hoa Dam, Hung Le, Truyen Tran, Kien Do.
Link

From Deep Learning to Deep Reasoning

Published/Accepted at KDD (Tutorial), 2021

Authors: Truyen Tran, Vuong Le, Hung Le, Thao M Le
Link

Robust Deep Reinforcement Learning for Extractive Legal Summarization

Published/Accepted at ICONIP, 2021

Authors: Duy-Hung Nguyen, Bao-Sinh Nguyen, Nguyen Viet Dung Nghiem, Dung Tien Le, Mim Amina Khatun, Minh-Tien Nguyen, Hung Le.
Link

Model-Based Episodic Memory Induces Dynamic Hybrid Controls

Published/Accepted at NeurIPS, 2021

Authors: Hung Le, Thommen Karimpanal George, Majid Abdolshah, Truyen Tran, Svetha Venkatesh
Code•Talk•Poster•Slides•PDF•Link

Episodic Policy Gradient Training

Published/Accepted at AAAI (Oral), 2022

Authors: Hung Le, Thommen Karimpanal George, Majid Abdolshah, Kien Do, Dung Nguyen, Svetha Venkatesh
Code•Talk•Slides•PDF•Link

Learning Theory of Mind via Dynamic Traits Attribution

Published/Accepted at AAMAS, 2022

Authors: Dung Nguyen, Phuoc Nguyen, Hung Le, Kien Do, Truyen Tran, Svetha Venkatesh
Link

Generative Pseudo-Inverse Memory

Published/Accepted at ICLR, 2022

Authors: Kha Pham, Hung Le, Man Ngo, Truyen Tran, Bao Ho, Svetha Venkatesh
Link

Make The Most of Prior Data: A Solution for Interactive Text Summarization with Preference Feedback

Published/Accepted at NAACL-Findings, 2022

Authors: Duy-Hung Nguyen, Nguyen Viet Dung Nghiem, Bao-Sinh Nguyen, Tien Dung Le, Minh-Tien Nguyen, Shahab Sabahi, Hung Le
Link

Neurocoder: General-Purpose Computation Using Stored Neural Programs

Published/Accepted at ICML (Spotlight), 2022

Authors: Hung Le, Svetha Venkatesh.
Code•PDF•Link

Towards Effective and Robust Neural Trojan Defenses via Input Filtering

Published/Accepted at ECCV, 2022

Authors: Kien Do, Haripriya Harikumar, Hung Le, Dung Nguyen, Truyen Tran, Santu Rana, Dang Nguyen, Willy Susilo, Svetha Venkatesh
Link

HYCEDIS: HYbrid Confidence Engine for Deep Document Intelligence System

Published/Accepted at ICONIP (Oral), 2022

Authors: Bao-Sinh Nguyen, Quang-Bach Tran, Tuan-Anh Nguyen Dang, Duc Nguyen, Hung Le.
Link

Improving Document Image Understanding with Reinforcement Finetuning

Published/Accepted at ICONIP (Oral), 2022

Authors: Bao-Sinh Nguyen, Dung Tien Le, Hieu M. Vu, Tuan-Anh D. Nguyen, Minh-Tien Nguyen, Hung Le
Link

Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation

Published/Accepted at NeurIPS, 2022

Authors: Kien Do, Hung Le, Dung Nguyen, Dang Nguyen, HARIPRIYA HARIKUMAR, Truyen Tran, Santu Rana, Svetha Venkatesh
Link

Functional Indirection Neural Estimator for Better Out-of-distribution Generalization

Published/Accepted at NeurIPS, 2022

Authors: Kha Pham, Hung Le, Man Ngo, Truyen Tran
Link

Learning to Constrain Policy Optimization with Virtual Trust Region

Published/Accepted at NeurIPS (Spotlight), 2022

Authors: Hung Le, Thommen Karimpanal George, Majid Abdolshah, Dung Nguyen, Kien Do, Sunil Gupta, Svetha Venkatesh
PDF•Link

Memory-Augmented Theory of Mind Network

Published/Accepted at AAAI, 2023

Authors: Dung Nguyen, Phuoc Nguyen, Hung Le, Kien Do, Svetha Venkatesh, Truyen Tran
Link

Improving Out-of-distribution Generalization with Indirection Representations

Published/Accepted at ICLR, 2023

Authors: Kha Pham, Hung Le, Man Ngo, Truyen Tran
Link

Social Motivation for Modelling Other Agents under Partial Observability in Decentralised Training

Published/Accepted at IJCAI, 2023

Authors: Dung Nguyen, Hung Le, Kien Do, Svetha Venkatesh, Truyen Tran
Link

The Application of Machine Learning in Micrometeoroid and Orbital Debris Impact Protection and Risk Assessment for Spacecraft

Published/Accepted at International Journal of Impact Engineering, 2023

Authors: Shannon Ryan, Neeraj Mohan Sushma, Hung Le, Arun Kumar A V, Santu Rana, Sevvandi Kandanaarachchi, Svetha Venkatesh
Link

Improving Domain Generalization with Interpolation Robustness

Published/Accepted at ACML, 2023

Authors: Ragja Palakkadavath, Thanh Nguyen-Tang, Hung Le, Svetha Venkatesh, Sunil Gupta
Link

Balanced Q-learning: Combining the Influence of Optimistic and Pessimistic Targets

Published/Accepted at Artificial Intelligence, 2023

Authors: Thommen George Karimpanal, Hung Le, Majid Abdolshah, Santu Rana, Sunil Gupta, Truyen Tran, Svetha Venkatesh.
Link

Universal Graph Continual Learning

Published/Accepted at Transactions on Machine Learning Research (TMLR) , 2023

Authors: Thanh Duc Hoang, Do Viet Tung, Duy-Hung Nguyen, Bao-Sinh Nguyen, Huy Hoang Nguyen, and Hung Le.
Link

Beyond Surprise: Improving Exploration Through Surprise Novelty

Published/Accepted at AAMAS (Oral), 2024

Authors: Hung Le, Kien Do, Dung Nguyen and Svetha Venkatesh
Code•PDF•Link

Diversifying Training Pool Predictability for Zero-shot Coordination: A Theory of Mind Approach

Published/Accepted at IJCAI, 2024

Authors: Dung Nguyen, Hung Le, Kien Do, Sunil Gupta, Svetha Venkatesh and Truyen Tran
Link

Variable-Agnostic Causal Exploration for Reinforcement Learning

Published/Accepted at ECML-PKDD, 2024

Authors: Minh Hoang Nguyen, Hung Le, Svetha Venkatesh
Code•Link

VRDSynth: Synthesizing Programs for Multilingual Visually Rich Document Information Extraction

Published/Accepted at ISSTA, 2024

Authors: Thanh-Dat Nguyen, Tung Do-Viet, Hung Nguyen-Duy, Tuan-Hai Luu, Hung Le, Bach Le, Patanamon (Pick) Thongtanunam
Link

Revisiting the Dataset Bias Problem from a Statistical Perspective

Published/Accepted at ECAI, 2024

Authors: Kien Do, Dung Nguyen, Hung Le, Thao Le, Dang Nguyen, Haripriya Harikumar, Truyen Tran, Santu Rana and Svetha Venkatesh
Link

Large Language Model Prompting With Episodic Memory

Published/Accepted at ECAI (Oral), 2024

Authors: Van Dai Do, Quan Tran, Svetha Venkatesh and Hung Le
PDF•Link

Plug, Play, and Generalize: Length Extrapolation with Pointer-Augmented Neural Memory

Published/Accepted at Transactions on Machine Learning Research (TMLR) , 2024

Authors: Hung Le, Dung Nguyen, Kien Do, Svetha Venkatesh, Truyen Tran
Link•Code

Fair Domain Generalization with Heterogeneous Sensitive Attributes Across Domains

Published/Accepted at WACV, 2024

Authors: Ragja Palakkadavath, Hung Le, Thanh Nguyen-Tang, Svetha Venkatesh, Sunil Gupta
Link

Multi-Reference Preference Optimization for Large Language Models

Published/Accepted at AAAI, 2025

Authors: Hung Le, Quan Hung Tran, Dung Nguyen, Kien Do, Saloni Mittal, Kelechi Ogueji, Svetha Venkatesh
Link•Code•Blog

talks

Theory behind conversational agents

Published: May 01, 2017

Event

Generalization for Good: A story on OCR evolution

Published: March 01, 2018

Video

From deep learning to deep reasoning

Published: August 15, 2021

Article

Neural machine reasoning

Published: August 25, 2021

Video

Memory for Lean Reinforcement Learning

Published: April 13, 2022

Slide•Video

Memory-Based Reinforcement Learning

Published: December 05, 2022

Website •Slide •Video

Unlocking Exploration: Self-Motivated Agents Thrive on Memory-Driven Curiosity

Published: May 06, 2024

Website•Slide•Code

Recent Advanced in LLM Finetuning and Uncertainty, Confidence and Hallucination in LLMs

Published: August 14, 2024

Post 1•Post 2

Towards Safe and Controlled Large Language Models

Published: November 25, 2024

Website •Slide •Code

Posts by Collection

grants

lectures

preprints

publications

talks

teaching