Phi Le Nguyen
YOU?
Author Swipe
View article: A review of instruction-guided image editing
A review of instruction-guided image editing Open
View article: Expressive and Scalable Quantum Fusion for Multimodal Learning
Expressive and Scalable Quantum Fusion for Multimodal Learning Open
The aim of this paper is to introduce a quantum fusion mechanism for multimodal learning and to establish its theoretical and empirical potential. The proposed method, called the Quantum Fusion Layer (QFL), replaces classical fusion scheme…
View article: ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge
ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge Open
This paper studies the black-box optimization task which aims to find the maxima of a black-box function using a static set of its observed input-output pairs. This is often achieved via learning and optimizing a surrogate function with th…
View article: Performance evaluation of ethereum consensus mechanisms in IoT-blockchain systems using resource-constrained devices
Performance evaluation of ethereum consensus mechanisms in IoT-blockchain systems using resource-constrained devices Open
The integration of IoT with blockchain technology enhances security and privacy through decentralized, trust-based systems, addressing challenges like single points of failure and limited scalability in traditional IoT architectures. This …
View article: Analysis and Visualization of QUIC Protocol Deployment in Vietnam
Analysis and Visualization of QUIC Protocol Deployment in Vietnam Open
View article: ConstStyle: Robust Domain Generalization with Unified Style Transformation
ConstStyle: Robust Domain Generalization with Unified Style Transformation Open
Deep neural networks often suffer performance drops when test data distribution differs from training data. Domain Generalization (DG) aims to address this by focusing on domain-invariant features or augmenting data for greater diversity. …
View article: New records on the botanical characteristics of Utricularia Pierrei distributed in lam dong province, Vietnam
New records on the botanical characteristics of Utricularia Pierrei distributed in lam dong province, Vietnam Open
The botanical characteristics of Utricularia pierrei Pellegr. from Ankroet Dam (Lam Dong Province, Vietnam) are described and illustrated. The result reveals that Utricularia pierrei exhibits typical traits of the genus Utricularia L. whil…
View article: Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding
Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding Open
Visual grounding (VG) is the capability to identify the specific regions in an image associated with a particular text description. In medical imaging, VG enhances interpretability by highlighting relevant pathological features correspondi…
View article: New Records on the Botanical Characteristics of Utriculariapierrei Distributed in Lam Dong Province, Vietnam
New Records on the Botanical Characteristics of Utriculariapierrei Distributed in Lam Dong Province, Vietnam Open
The botanical characteristics of Utricularia pierrei Pellegr. from Ankroet Dam (Lam Dong Province, Vietnam) are described and illustrated. The result reveals that Utricularia pierrei exhibits typical traits of the genus Utricularia while h…
View article: Localizing Before Answering: A Hallucination Evaluation Benchmark for Grounded Medical Multimodal LLMs
Localizing Before Answering: A Hallucination Evaluation Benchmark for Grounded Medical Multimodal LLMs Open
Medical Large Multi-modal Models (LMMs) have demonstrated remarkable capabilities in medical data interpretation. However, these models frequently generate hallucinations contradicting source evidence, particularly due to inadequate locali…
View article: AIM: an accurate and explainable model for ATAC to GEX translation and pathway analysis
AIM: an accurate and explainable model for ATAC to GEX translation and pathway analysis Open
The development of multimodal technologies has enabled the simultaneous measurement of various cellular modalities, such as chromatin accessibility (ATAC), gene expression (GEX), and surface protein abundance in single cells. However, the …
View article: On-device diagnostic recommendation with heterogeneous federated BlockNets
On-device diagnostic recommendation with heterogeneous federated BlockNets Open
The evolution of edge computing has advanced the accessibility of E-health recommendation services, encompassing areas such as medical consultations, prescription guidance, and diagnostic assessments. Traditional methodologies predominantl…
View article: Boosting Offline Optimizers with Surrogate Sensitivity
Boosting Offline Optimizers with Surrogate Sensitivity Open
Offline optimization is an important task in numerous material engineering domains where online experimentation to collect data is too expensive and needs to be replaced by an in silico maximization of a surrogate of the black-box function…
View article: Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniques
Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniques Open
Offline optimization has recently emerged as an increasingly popular approach to mitigate the prohibitively expensive cost of online experimentation. The key idea is to learn a surrogate of the black-box function that underlines the target…
View article: NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions
NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions Open
Understanding the inner workings of neural networks is essential for enhancing model performance and interpretability. Current research predominantly focuses on examining the connection between individual neurons and the model's final pred…
View article: Bridging Classification and Segmentation in Osteosarcoma Assessment via Foundation and Discrete Diffusion Models
Bridging Classification and Segmentation in Osteosarcoma Assessment via Foundation and Discrete Diffusion Models Open
Osteosarcoma, the most common primary bone cancer, often requires accurate necrosis assessment from whole slide images (WSIs) for effective treatment planning and prognosis. However, manual assessments are subjective and prone to variabili…
View article: Boosting Air Quality Interpolation with Satellite Images and Graph Neural Network
Boosting Air Quality Interpolation with Satellite Images and Graph Neural Network Open
View article: MLAlgo-Bench: Can Machines Implement Machine Learning Algorithms?
MLAlgo-Bench: Can Machines Implement Machine Learning Algorithms? Open
View article: M³-SLR: Self-Supervised Pretraining With MaxFlow MaskFeat for Improved Multi-View Sign Language Representation
M³-SLR: Self-Supervised Pretraining With MaxFlow MaskFeat for Improved Multi-View Sign Language Representation Open
Sign Language Recognition (SLR) is crucial for facilitating communication with the hard-of-hearing community, yet remains significantly challenged by factors such as inter-signer variations, self-occlusion, and the critical issue of Visual…
View article: Certified Unlearning for Federated Recommendation
Certified Unlearning for Federated Recommendation Open
Recommendation systems play a crucial role in providing web-based suggestion utilities by leveraging user behavior, preferences, and interests. In the context of privacy concerns and the proliferation of handheld devices, federated recomme…
View article: Instruction-Guided Editing Controls for Images and Multimedia: A Survey in LLM era
Instruction-Guided Editing Controls for Images and Multimedia: A Survey in LLM era Open
The rapid advancement of large language models (LLMs) and multimodal learning has transformed digital content creation and manipulation. Traditional visual editing tools require significant expertise, limiting accessibility. Recent strides…
View article: Privacy-preserving explainable AI: a survey
Privacy-preserving explainable AI: a survey Open
As the adoption of explainable AI (XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preservin…
View article: CT to PET Translation: A Large-scale Dataset and Domain-Knowledge-Guided Diffusion Approach
CT to PET Translation: A Large-scale Dataset and Domain-Knowledge-Guided Diffusion Approach Open
Positron Emission Tomography (PET) and Computed Tomography (CT) are essential for diagnosing, staging, and monitoring various diseases, particularly cancer. Despite their importance, the use of PET/CT systems is limited by the necessity fo…
View article: FedMAC: Tackling Partial-Modality Missing in Federated Learning with Cross-Modal Aggregation and Contrastive Regularization
FedMAC: Tackling Partial-Modality Missing in Federated Learning with Cross-Modal Aggregation and Contrastive Regularization Open
Federated Learning (FL) is a method for training machine learning models using distributed data sources. It ensures privacy by allowing clients to collaboratively learn a shared global model while storing their data locally. However, a sig…
View article: FedCert: Federated Accuracy Certification
FedCert: Federated Accuracy Certification Open
Federated Learning (FL) has emerged as a powerful paradigm for training machine learning models in a decentralized manner, preserving data privacy by keeping local data on clients. However, evaluating the robustness of these models against…
View article: Higher-order knowledge-enhanced recommendation with heterogeneous hypergraph multi-attention
Higher-order knowledge-enhanced recommendation with heterogeneous hypergraph multi-attention Open
View article: Heterogeneous Hypergraph Embedding for Recommendation Systems
Heterogeneous Hypergraph Embedding for Recommendation Systems Open
Recent advancements in recommender systems have focused on integrating knowledge graphs (KGs) to leverage their auxiliary information. The core idea of KG-enhanced recommenders is to incorporate rich semantic information for more accurate …
View article: A Contrastive Learning and Graph-based Approach for Missing Modalities in Multimodal Federated Learning
A Contrastive Learning and Graph-based Approach for Missing Modalities in Multimodal Federated Learning Open
Federated Learning has emerged as a decentralized method for training machine learning models using distributed data sources. It ensures privacy by allowing clients to collaboratively learn a shared global model while keeping their data st…
View article: Hierarchical Federated Learning in MEC Networks with Knowledge Distillation
Hierarchical Federated Learning in MEC Networks with Knowledge Distillation Open
Modern automobiles are equipped with advanced computing capabilities, allowing them to become powerful computing units capable of processing a large amount of data and training machine learning models. However, machine learning algorithms …
View article: Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience
Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience Open
Federated learning (FL) has recently emerged as a compelling machine learning paradigm, prioritizing the protection of privacy for training data. The increasing demand to address issues such as ``the right to be forgotten'' and combat data…