Hung Lê
YOU?
Author Swipe
View article: Pre-clinical evaluation of immunogenicity and protective efficacy of a pan-orthoebolavirus virus-like particle (VLP) vaccine 3075
Pre-clinical evaluation of immunogenicity and protective efficacy of a pan-orthoebolavirus virus-like particle (VLP) vaccine 3075 Open
Description Development of pan-orthoebolavirus vaccines to prevent Ebola disease and to induce durable protective immunity remains an important unmet need. Current Ebola virus (EBOV) vaccines have been reported to protect humans only again…
View article: CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning
CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning Open
Large language model (LLM) agents-especially smaller, open-source models-often produce causally invalid or incoherent actions in collaborative tasks due to their reliance on surface-level correlations rather than grounded causal reasoning.…
View article: DmC: Nearest Neighbor Guidance Diffusion Model for Offline Cross-domain Reinforcement Learning
DmC: Nearest Neighbor Guidance Diffusion Model for Offline Cross-domain Reinforcement Learning Open
Cross-domain offline reinforcement learning (RL) seeks to enhance sample efficiency in offline RL by utilizing additional offline source datasets. A key challenge is to identify and utilize source samples that are most relevant to the targ…
View article: Comprehensive Statistical Analysis for Characterizing Water Quality Assessment in the Mekong Delta: Trends, Variability, and Key Influencing Factors
Comprehensive Statistical Analysis for Characterizing Water Quality Assessment in the Mekong Delta: Trends, Variability, and Key Influencing Factors Open
The Mekong Delta, an important agricultural and economic hub in Vietnam, has suffered from severe water quality issues caused by both natural and anthropogenic forces. This paper aims to conduct a rational statistical approach to evaluate …
View article: Approximate Light Spanners in Planar Graphs
Approximate Light Spanners in Planar Graphs Open
In their seminal paper, Althöfer et al. (DCG 1993) introduced the {\em greedy spanner} and showed that, for any weighted planar graph $G$, the weight of the greedy $(1+ε)$-spanner is at most $(1+\frac{2}ε) \cdot w(MST(G))$, where $w(MST(G)…
View article: Hybrid Cross-domain Robust Reinforcement Learning
Hybrid Cross-domain Robust Reinforcement Learning Open
Robust reinforcement learning (RL) aims to learn policies that remain effective despite uncertainties in its environment, which frequently arise in real-world applications due to variations in environment dynamics. The robust RL methods le…
View article: Beyond the Known: Decision Making with Counterfactual Reasoning Decision Transformer
Beyond the Known: Decision Making with Counterfactual Reasoning Decision Transformer Open
Decision Transformers (DT) play a crucial role in modern reinforcement learning, leveraging offline datasets to achieve impressive results across various domains. However, DT requires high-quality, comprehensive data to perform optimally. …
View article: LaGR-SEQ: Language-guided reinforcement learning with sample-efficient querying
LaGR-SEQ: Language-guided reinforcement learning with sample-efficient querying Open
Large language models (LLMs) have recently demonstrated their impressive ability to provide context-aware responses via text. This ability could potentially be used to predict plausible solutions in sequential decision making tasks pertain…
View article: Active Advantage-Aligned Online Reinforcement Learning with Offline Data
Active Advantage-Aligned Online Reinforcement Learning with Offline Data Open
Online reinforcement learning (RL) enhances policies through direct interactions with the environment, but faces challenges related to sample efficiency. In contrast, offline RL leverages extensive pre-collected data to learn policies, but…
View article: Navigation in brain networks is possible using only local measures
Navigation in brain networks is possible using only local measures Open
A major question in neuroscience is how the brain structure facilitates its complex functions via the synchronous activity of separate parts of the brain. Recent research has indicated that the mechanisms underlying this facilitation are b…
View article: Large Language Model Prompting with Episodic Memory
Large Language Model Prompting with Episodic Memory Open
Prompt optimization is essential for enhancing the performance of Large Language Models (LLMs) in a range of Natural Language Processing (NLP) tasks, particularly in scenarios of few-shot learning where training examples are incorporated d…
View article: Physics-Informed Machine Learning for Predicting the Ballistic Limit of Whipple Shields
Physics-Informed Machine Learning for Predicting the Ballistic Limit of Whipple Shields Open
Introduction Ballistic limit equations (BLEs) define the performance of a spacecraft structure or component impacted by a space debris particle, typically in terms of a critical projectile diameter for a given impact velocity and obliquity…
View article: Large Language Models Prompting With Episodic Memory
Large Language Models Prompting With Episodic Memory Open
Prompt optimization is essential for enhancing the performance of Large Language Models (LLMs) in a range of Natural Language Processing (NLP) tasks, particularly in scenarios of few-shot learning where training examples are incorporated d…
View article: Combining Deep Reinforcement Learning and Search with Generative Models for Game-Theoretic Opponent Modeling
Combining Deep Reinforcement Learning and Search with Generative Models for Game-Theoretic Opponent Modeling Open
Opponent modeling methods typically involve two crucial steps: building a belief distribution over opponents' strategies, and exploiting this opponent model by playing a best response. However, existing approaches typically require domain-…
View article: Less is More: Sparse Watermarking in LLMs with Enhanced Text Quality
Less is More: Sparse Watermarking in LLMs with Enhanced Text Quality Open
With the widespread adoption of Large Language Models (LLMs), concerns about potential misuse have emerged. To this end, watermarking has been adapted to LLM, enabling a simple and effective way to detect and monitor generated text. Howeve…
View article: A Novel PIML Architecture with Innovative Learning Paradigm Applied in Battery Prognostics
A Novel PIML Architecture with Innovative Learning Paradigm Applied in Battery Prognostics Open
International audience
View article: Enhancing Length Extrapolation in Sequential Models with Pointer-Augmented Neural Memory
Enhancing Length Extrapolation in Sequential Models with Pointer-Augmented Neural Memory Open
We propose Pointer-Augmented Neural Memory (PANM) to help neural networks understand and apply symbol processing to new, longer sequences of data. PANM integrates an external neural memory that uses novel physical addresses and pointer man…
View article: Revisiting the Dataset Bias Problem from a Statistical Perspective
Revisiting the Dataset Bias Problem from a Statistical Perspective Open
In this paper, we study the "dataset bias" problem from a statistical standpoint, and identify the main cause of the problem as the strong correlation between a class attribute u and a non-class attribute b in the input x, represented by p…
View article: Moonshot: Towards Controllable Video Generation and Editing with Multimodal Conditions
Moonshot: Towards Controllable Video Generation and Editing with Multimodal Conditions Open
Most existing video diffusion models (VDMs) are limited to mere text conditions. Thereby, they are usually lacking in control over visual appearance and geometry structure of the generated videos. This work presents Moonshot, a new video g…
View article: Approximation Algorithms for the Airport and Railway Problem
Approximation Algorithms for the Airport and Railway Problem Open
In this paper, we present approximation algorithms for the airport and railway problem (AR) on several classes of graphs. The AR problem, introduced by [Anna Adamaszek et al., 2016], is a combination of the Capacitated Facility Location pr…
View article: SurvTimeSurvival: Survival Analysis On The Patient With Multiple Visits/Records
SurvTimeSurvival: Survival Analysis On The Patient With Multiple Visits/Records Open
The accurate prediction of survival times for patients with severe diseases remains a critical challenge despite recent advances in artificial intelligence. This study introduces "SurvTimeSurvival: Survival Analysis On Patients With Multip…
View article: Balanced Q-learning: Combining the influence of optimistic and pessimistic targets
Balanced Q-learning: Combining the influence of optimistic and pessimistic targets Open
The optimistic nature of the Q−learning target leads to an overestimation bias, which is an inherent problem associated with standard Q−learning. Such a bias fails to account for the possibility of low returns, particularly in risky scenar…
View article: Universal Graph Continual Learning
Universal Graph Continual Learning Open
We address catastrophic forgetting issues in graph learning as incoming data transits from one to another graph distribution. Whereas prior studies primarily tackle one setting of graph continual learning such as incremental node classific…
View article: LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying
LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying Open
Large language models (LLMs) have recently demonstrated their impressive ability to provide context-aware responses via text. This ability could potentially be used to predict plausible solutions in sequential decision making tasks pertain…