Binh T. Nguyen
YOU?
Author Swipe
View article: The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models
The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models Open
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key method for improving Large Language Models' reasoning capabilities, yet recent evidence suggests it may paradoxically shrink the reasoning boundary rather than expa…
View article: A RAG Approach for Multi-Modal Open-ended Lifelog Question-Answering
A RAG Approach for Multi-Modal Open-ended Lifelog Question-Answering Open
Lifelogging is the passive collection, storage and analysis of daily data through wearable sensors. Question Answering (QA) for lifelog data enables natural language interactions with personal daily life records, providing insights into in…
View article: Real-time flood forecasting using time-varying parameter hydrological model: case study for Ta Trach reservoir
Real-time flood forecasting using time-varying parameter hydrological model: case study for Ta Trach reservoir Open
Flood forecasting for reservoir operation is a complex and challenging subject. It is, however, fundamental for minimizing damage and maximizing economic efficiency in reservoir management. Currently, real-time flood forecasting represents…
View article: I-MPN: inductive message passing network for efficient human-in-the-loop annotation of mobile eye tracking data
I-MPN: inductive message passing network for efficient human-in-the-loop annotation of mobile eye tracking data Open
View article: Sequence Transferability and Task Order Selection in Continual Learning
Sequence Transferability and Task Order Selection in Continual Learning Open
In continual learning, understanding the properties of task sequences and their relationships to model performance is important for developing advanced algorithms with better accuracy. However, efforts in this direction remain underdevelop…
View article: DPERC: Direct Parameter Estimation for Mixed Data
DPERC: Direct Parameter Estimation for Mixed Data Open
The covariance matrix is a foundation in numerous statistical and machine-learning applications such as Principle Component Analysis, Correlation Heatmap, etc. However, missing values within datasets present a formidable obstacle to accura…
View article: Boosting Insect Pest Recognition with Deep-Wide Learning
Boosting Insect Pest Recognition with Deep-Wide Learning Open
View article: The hero-Zen practitioner protagonist in Haruki Murakami’s novels: An analysis from Joseph Campbell’s hero’s journey monomyth
The hero-Zen practitioner protagonist in Haruki Murakami’s novels: An analysis from Joseph Campbell’s hero’s journey monomyth Open
View article: Missing data imputation for noisy time-series data and applications in healthcare
Missing data imputation for noisy time-series data and applications in healthcare Open
Healthcare time series data is vital for monitoring patient activity but often contains noise and missing values due to various reasons such as sensor errors or data interruptions. Imputation, i.e., filling in the missing values, is a comm…
View article: NGHIÊN CỨU THÀNH PHẦN LOÀI VÀ PHÂN BỐ THÂN MỀM CHÂN BỤNG Ở CẠN (MOLLUSCA: GASTROPODA) KHU VỰC VEN BIỂN THÀNH PHỐ ĐÀ NẴNG
NGHIÊN CỨU THÀNH PHẦN LOÀI VÀ PHÂN BỐ THÂN MỀM CHÂN BỤNG Ở CẠN (MOLLUSCA: GASTROPODA) KHU VỰC VEN BIỂN THÀNH PHỐ ĐÀ NẴNG Open
Bài báo đề cập về kết quả nghiên cứu về thành phần loài Thân mềm Chân bụng ở cạn vùng ven biển thành phố Đà Nẵng được tiến hành vào 6/2022 – 10/2023. Qua phân tích đã xác định được 17 loài, trong số các loài được định danh có 15 loài có vỏ…
View article: Enhancing legal research through knowledge-infused information retrieval for Vietnamese labor law
Enhancing legal research through knowledge-infused information retrieval for Vietnamese labor law Open
The role of intelligent information retrieval systems in legal research optimization has become increasingly recognized. There are many methods for exhibiting advance mentsin the proficient retrieval of legal documents. However, those meth…
View article: The impact of data imputation on air quality prediction problem
The impact of data imputation on air quality prediction problem Open
With rising environmental concerns, accurate air quality predictions have become paramount as they help in planning preventive measures and policies for potential health hazards and environmental problems caused by poor air quality. Most o…
View article: Concept-Based and Embedding-Based Models in Lifelog Retrieval: An Empirical Comparison of Performance
Concept-Based and Embedding-Based Models in Lifelog Retrieval: An Empirical Comparison of Performance Open
Many lifelog retrieval systems have been introduced that apply various approaches to their search engines. The traditional method was to match concepts, which are visual objects detected in images and semantic queries. This concept-based a…
View article: Multimodal scene-graph matching for cheapfakes detection
Multimodal scene-graph matching for cheapfakes detection Open
The development of technology and social media platforms has led to the proliferation of fake news, including the cheapfakes problem. Cheapfakes can be produced easily and spread quickly; a common type is out-of-context misinformation. It …
View article: Oversampling and imputation for imbalanced missing data
Oversampling and imputation for imbalanced missing data Open
Oversampling and imputation for imbalanced missing data Imbalanced data is a widespread issue that is naturally occurring. For instance, fraudulent banking transactions are less frequent than normal transactions, and the number of cancer c…
View article: LifeSeeker 6.0: Leveraging the linguistic aspect of the lifelog system in LSC'24
LifeSeeker 6.0: Leveraging the linguistic aspect of the lifelog system in LSC'24 Open
Supporting effective access to digital lifelogs is a challenging research task because of both the volume and variety of multimodal lifelog data, as well as the many and diverse types of information need that should be supported. In this p…
View article: MyEachtraX: Lifelog Question Answering on Mobile
MyEachtraX: Lifelog Question Answering on Mobile Open
Your whole life in your pocket. That is the premise of lifelogging, a technology that captures and stores every moment of your life in digital form. Built on top of MyEachtra and the lifelog question-answering pipeline, MyEachtraX is a mob…
View article: MemoriEase 2.0: A Conversational Lifelog Retrieve System for LSC'24
MemoriEase 2.0: A Conversational Lifelog Retrieve System for LSC'24 Open
Lifelog retrieval plays an important role in memory support for lifeloggers. It helps the lifeloggers to browse, search and navigate their life moments from the lifelog data. However, the volume and variety of lifelog data are enormous and…
View article: I-MPN: Inductive Message Passing Network for Efficient Human-in-the-Loop Annotation of Mobile Eye Tracking Data
I-MPN: Inductive Message Passing Network for Efficient Human-in-the-Loop Annotation of Mobile Eye Tracking Data Open
Comprehending how humans process visual information in dynamic settings is crucial for psychology and designing user-centered interactions. While mobile eye-tracking systems combining egocentric video and gaze signals can offer valuable in…
View article: MemoriQA: A Question-Answering Lifelog Dataset
MemoriQA: A Question-Answering Lifelog Dataset Open
Lifelogging can be referred to as the process of passively collecting data on an individual's daily life. Lifelog data provides a large amount of information which can be used to understand the lifelogger's lifestyle and preferences. This …
View article: Generative Conditional Distributions by Neural (Entropic) Optimal Transport
Generative Conditional Distributions by Neural (Entropic) Optimal Transport Open
Learning conditional distributions is challenging because the desired outcome is not a single distribution but multiple distributions that correspond to multiple instances of the covariates. We introduce a novel neural entropic optimal tra…
View article: MemoriLens: a Low-cost Lifelog Camera Using Raspberry Pi Zero
MemoriLens: a Low-cost Lifelog Camera Using Raspberry Pi Zero Open
Lifelogging is the process of automatically logging data about an individual's daily life, which can then be used in various domains, such as behavior analysis and health monitoring. Various technological devices, including wearable camera…
View article: Accelerating Transformers with Spectrum-Preserving Token Merging
Accelerating Transformers with Spectrum-Preserving Token Merging Open
Increasing the throughput of the Transformer architecture, a foundational component used in numerous state-of-the-art models for vision and language tasks (e.g., GPT, LLaVa), is an important problem in machine learning. One recent and effe…
View article: Analyzing the correlation between protein expression and sequence-related features of mRNA and protein in Escherichia coli K-12 MG1655 model
Analyzing the correlation between protein expression and sequence-related features of mRNA and protein in Escherichia coli K-12 MG1655 model Open
It was necessary to have a tool that could predict the amount of protein and optimize the gene sequences to produce recombinant proteins efficiently. The Transim model published by Tuller et al . in 2018 can calculate the translation rate …
View article: Small Flying Object Detection and Tracking in Digital Airport Tower Through Spatial-Temporal Convnets
Small Flying Object Detection and Tracking in Digital Airport Tower Through Spatial-Temporal Convnets Open
View article: Interactive Question Answering for Multimodal Lifelog Retrieval
Interactive Question Answering for Multimodal Lifelog Retrieval Open
Supporting Question Answering (QA) tasks is the next step for lifelog retrieval systems, similar to the progression of the parent field of information retrieval. In this paper, we propose a new pipeline to tackle the QA task in the context…
View article: ViEcomRec: A Dataset for Recommendation in Vietnamese E-Commerce
ViEcomRec: A Dataset for Recommendation in Vietnamese E-Commerce Open
Recent years have seen the increasing popularity of e-commerce platforms which have changed the shopping behaviour of customers. Valuable data from products, customers, and purchases on such e-commerce platforms enable the delivery of pers…
View article: Semidefinite Relaxations of the Gromov-Wasserstein Distance
Semidefinite Relaxations of the Gromov-Wasserstein Distance Open
The Gromov-Wasserstein (GW) distance is an extension of the optimal transport problem that allows one to match objects between incomparable spaces. At its core, the GW distance is specified as the solution of a non-convex quadratic program…
View article: Sequencing p72 gene of field strain of African swine fever virus (ASFV) in Vietnam and generation of enhanced immunogenic fusion protein G-p72 potentially expressed as a recombinant antigen in ASFV subunit vaccine
Sequencing p72 gene of field strain of African swine fever virus (ASFV) in Vietnam and generation of enhanced immunogenic fusion protein G-p72 potentially expressed as a recombinant antigen in ASFV subunit vaccine Open
Protein p72 is the major surface protein of African swine fever virus (ASFV), which is immunogenic and can prime the host to elicit a protective immune response, while G protein is the surface glycoprotein of vesicular stomatitis virus (VS…
View article: On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation
On the Out of Distribution Robustness of Foundation Models in Medical Image Segmentation Open
Constructing a robust model that can effectively generalize to test samples under distribution shifts remains a significant challenge in the field of medical imaging. The foundational models for vision and language, pre-trained on extensiv…