WACV VisionDocsFeb 2026
Improving End-to-End Models for Form Understanding with Synthetic Ground Truth Pairs
Methods for improving end-to-end document understanding models by leveraging synthetic ground truth pairs of commonly filled form data.
CAPTAIN'S LOG
Publications
Our published research. We focus on reproducible work with open code and data.
JNSM2024
Benchmarking Large Language Models for Log Analysis, Security, and Interpretation
Benchmarking LLMs (BERT, RoBERTa, GPT-2, GPT-Neo) for security log analysis. Introduces LLM4Sec pipeline achieving 0.998 F1-Score.
Annals of Telecom2024
Large Language Models and Unsupervised Feature Learning: Implications for Log Analysis
Exploring LLM embeddings for distinguishing behaviors in log files via unsupervised learning for anomaly detection.
CSNet2023
Exploring Semantic vs. Syntactic Features for Unsupervised Learning on Application Log Files
Comparing semantic and syntactic feature extraction approaches for unsupervised anomaly detection in application logs.
it - Info Tech2022
Exploring Syntactical Features for Anomaly Detection in Application Logs
Analyzing lightweight syntactical feature extraction techniques from information retrieval for log abstraction in security.
arXiv2021
NoFADE: Analyzing Diminishing Returns on CO2 Investment
Novel entropy-based metric to quantify model-dataset-complexity relationships and analyze environmental impact of CV methods.
CVPR Workshop2021
Reconsidering CO2 Emissions From Computer Vision
Addressing climate change impact from the Computer Vision community and proposing methods to limit environmental footprint.
ICCV Workshop2021
CONet: Channel Optimization for Convolutional Neural Networks
Neural architecture optimization focusing on channel configurations for improved efficiency in convolutional networks.
Collaborate With Us
Interested in research collaboration? We're always looking to work with researchers who share our commitment to open science.
Get In Touch