Radu State
YOU?
Author Swipe
View article: Uncovering Zero-Shot Generalization Gaps in Time-Series Foundation Models Using Real-World Videos
Uncovering Zero-Shot Generalization Gaps in Time-Series Foundation Models Using Real-World Videos Open
Recent research on time-series foundation models (TSFMs) has underscored the scarcity of real-world data, often supplemented with synthetic sources in existing datasets, whose generalizability remains however debated. As such, in this work…
View article: Vision Transformer-Based Time-Series Image Reconstruction for Cloud-Filling Applications
Vision Transformer-Based Time-Series Image Reconstruction for Cloud-Filling Applications Open
Cloud cover in multispectral imagery (MSI) poses significant challenges for early season crop mapping, as it leads to missing or corrupted spectral information. Synthetic aperture radar (SAR) data, which is not affected by cloud interferen…
View article: Small Language Models in the Real World: Insights from Industrial Text Classification
Small Language Models in the Real World: Insights from Industrial Text Classification Open
With the emergence of ChatGPT, Transformer models have significantly advanced text classification and related tasks. Decoder-only models such as Llama exhibit strong performance and flexibility, yet they suffer from inefficiency on inferen…
View article: LongKey: Keyphrase Extraction for Long Documents
LongKey: Keyphrase Extraction for Long Documents Open
In an era of information overload, manually annotating the vast and growing corpus of documents and scholarly papers is increasingly impractical. Automated keyphrase extraction addresses this challenge by identifying representative terms w…
View article: Cross-Sector Market Regime Forecasting with LLM-Augmented News Analysis
Cross-Sector Market Regime Forecasting with LLM-Augmented News Analysis Open
This paper investigates the utilization of news in predicting market regimes. The findings illustrate that employing an ensemble of multiple FinBERT models can outperform straightforward time-series prediction by 73% in accuracy and 110% i…
View article: WallStreetFeds: Client-Specific Tokens as Investment Vehicles in Federated Learning
WallStreetFeds: Client-Specific Tokens as Investment Vehicles in Federated Learning Open
Federated Learning (FL) is a collaborative machine learning paradigm which allows participants to collectively train a model while training data remains private. This paradigm is especially beneficial for sectors like finance, where data p…
View article: BLU-SynTra: Distinguish Synergies and Trade-offs between Sustainable Development Goals Using Small Language Models
BLU-SynTra: Distinguish Synergies and Trade-offs between Sustainable Development Goals Using Small Language Models Open
International audience
View article: Cross Domain Early Crop Mapping with Label Spaces Discrepancies using MultiCropGAN
Cross Domain Early Crop Mapping with Label Spaces Discrepancies using MultiCropGAN Open
Mapping target crops before the harvest season for regions lacking crop-specific ground truth is critical for global food security. Utilizing multispectral remote sensing and domain adaptation methods, prior studies strive to produce preci…
View article: To Squelch or not to Squelch: Enabling Improved Message Dissemination on the XRP Ledger
To Squelch or not to Squelch: Enabling Improved Message Dissemination on the XRP Ledger Open
International audience
View article: Cropland Quantum Learning: A Hybrid Quantum-Classical Neural Network for Cropland Classification
Cropland Quantum Learning: A Hybrid Quantum-Classical Neural Network for Cropland Classification Open
peer reviewed
View article: Cross Domain Early Crop Mapping using CropSTGAN
Cross Domain Early Crop Mapping using CropSTGAN Open
Driven by abundant satellite imagery, machine learning-based approaches have recently been promoted to generate high-resolution crop cultivation maps to support many agricultural applications. One of the major challenges faced by these app…
View article: Cross Domain Early Crop Mapping Using CropSTGAN
Cross Domain Early Crop Mapping Using CropSTGAN Open
Driven by abundant satellite imagery, machine learning-based approaches have recently been promoted to generate high-resolution crop cultivation maps to support many agricultural applications. One of the major challenges faced by these app…
View article: Pub/Sub Dissemination on the XRP Ledger
Pub/Sub Dissemination on the XRP Ledger Open
The XRP Ledger is one of the oldest and most well-established blockchains, using a particular type of consensus mechanism that differs from the typical Proof of Work and Proof of Stake. The underlying p2p network uses flooding to dis-semin…
View article: NLAC: A Self-Maintained Trust Overlay for the XRP Ledger
NLAC: A Self-Maintained Trust Overlay for the XRP Ledger Open
This paper presents NLAC, a framework for creating, managing, and maintaining trusted Unique Node Lists (UNLs) for the XRP Ledger. NLAC consists of three modules that automate the generation of UNLs, including membership management, classi…
View article: Early Crop Mapping Using Dynamic Ecoregion Clustering: A USA-Wide Study
Early Crop Mapping Using Dynamic Ecoregion Clustering: A USA-Wide Study Open
Mapping target crops earlier than the harvest period is an essential task for improving agricultural productivity and decision-making. This paper presents a new method for early crop mapping for the entire conterminous USA (CONUS) land are…
View article: Federated Byzantine Agreement Protocol Robustness to Targeted Network Attacks
Federated Byzantine Agreement Protocol Robustness to Targeted Network Attacks Open
International audience
View article: Blockly2Hooks: Smart Contracts for Everyone with the XRP Ledger and Google Blockly
Blockly2Hooks: Smart Contracts for Everyone with the XRP Ledger and Google Blockly Open
Recent technologies such as inter-ledger payments, non-fungible tokens, and smart contracts are all fruited from the ongoing development of Distributed Ledger Technologies. The foreseen trend is that they will play an increasingly visible …
View article: XRP-NDN overlay: Improving the Communication Efficiency of Consensus-Validation based Blockchains with an NDN Overlay
XRP-NDN overlay: Improving the Communication Efficiency of Consensus-Validation based Blockchains with an NDN Overlay Open
With growing adoption of Distributed Ledger Technologies, their networks must scale while maintaining efficient communication for the underlying consensus and replication mechanisms. New content distribution concepts like Named Data Networ…
View article: Topology Analysis of the XRP Ledger
Topology Analysis of the XRP Ledger Open
International audience
View article: G-HIN2Vec: Distributed heterogeneous graph representations for cardholder transactions
G-HIN2Vec: Distributed heterogeneous graph representations for cardholder transactions Open
peer reviewed
View article: XRP-NDN Overlay: Improving the Communication Efficiency of Consensus-Validation based Blockchains with an NDN Overlay
XRP-NDN Overlay: Improving the Communication Efficiency of Consensus-Validation based Blockchains with an NDN Overlay Open
With the growing adoption of Distributed Ledger Technologies and the subsequent scaling of these networks, there is an inherent need for efficient and resilient communication used by the underlying consensus and replication mechanisms. Whi…
View article: Probabilistic Edge Multicast Routing for the XRP Network
Probabilistic Edge Multicast Routing for the XRP Network Open
International audience