2.9k citations · 3.1k across the 3 of their papers we have counts for
4 papers
Scan or Index? large Evidence Coverage, Answer Quality, and Cost in Long-Document RAG
Juan Terven, Diana-Margarita Córdova-Esparza, Julio-Alejandro Romero-González +5
Scanning every passage in a long document seems thorough, but does it preserve more useful evidence or produce better answers? We compare 11 retrieval configurations spanning lexic…
A Strong Balanced-Softmax Classifier-Retraining Baseline for Long-Tailed Recognition
Juan Terven, Diana Margarita Córdova Esparza, Julio Alejandro Romero Gonzalez +4
Long-tailed recognition methods often modify losses, margins, or representations to reduce the dominance of frequent classes. We ask whether, after Balanced Softmax training, the r…
Loss Functions and Metrics in Deep Learning
Juan Terven, Diana M. Cordova-Esparza, Alfonso Ramirez-Pedraza +2
This paper presents a comprehensive review of loss functions and performance metrics in deep learning, highlighting key developments and practical insights across diverse applicati…
A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS
Juan Terven, Diana Cordova-Esparza
YOLO has become a central real-time object detection system for robotics, driverless cars, and video monitoring applications. We present a comprehensive analysis of YOLO's evolutio…