GitHub

SFTTrainer causes PyTorch Distributed deadlock detection timeout with large datasets during preprocessing

When using SFTTrainer with large datasets that require long preprocessing times (over 30 minutes), the training process consistently fails due to a PyTorch ...
IEEE

Real-World Code Vulnerability Detection Framework: From Data Preprocessing to Multi-Feature Fusion Detection

Abstract: Code vulnerability detection (CVD) is a critical approach to ensuring the security, stability, and reliability of software. When exploited by malicious actors or hackers, code ...
GitHub

Clarify exact numeric preprocessing for tutorial public datasets (e.g., Jurkat)

Could you please clarify the exact numeric preprocessing steps applied to the tutorial public datasets (e.g., Jurkat, K562, RPE1, HEK293T/HEPG2), beyond the cell/target filtering described? For the ...
Semiconductor Engineering

Largest High-Quality Verilog Dataset for LLM Fine-Tuning (Univ. of Florida)

A new technical paper titled “VerilogDB: The Largest, Highest-Quality Dataset with a Preprocessing Framework for LLM-based RTL Generation” was published by researchers at the University of Florida.
Frontiers

DTCNet: finger flexion decoding with three-dimensional ECoG data

School of Big Data, Zhuhai College of Science and Technology, Zhuhai, China ECoG signals are widely used in Brain-Computer Interfaces (BCIs) due to their high spatial resolution and superior signal ...
Geeky Gadgets

How to Extract Specific Data Automatically from Cells in Excel : 2025 Guide

Have you ever stared at a massive spreadsheet, overwhelmed by the chaos of mixed data—names, IDs, codes—all crammed into single cells? It’s a common frustration for anyone managing large datasets in ...
Frontiers

Accurate V2X traffic prediction with deep learning architectures

Vehicle-to-Everything (V2X) communication promises to revolutionize road safety and efficiency. However, challenges in data sharing and network reliability impede its full realization. This paper ...
IEEE

Deep Minimax Classifiers for Imbalanced Datasets With a Small Number of Minority Samples

Abstract: The concept of a minimax classifier is well-established in statistical decision theory, but its implementation via neural networks remains challenging, particularly in scenarios with ...
Scientific Research Publishing

Credit Score Classification Using Advanced Machine Learning: A Comprehensive Approach ()

1 Department of Computer Science, Rutgers University, New Brunswick, NJ, USA. 2 Department of Computer Science, Rochester Institute of Technology, Rochester, NY, USA. This paper presents a ...