Brandone Fonya
MEng. Artificial Intelligence • Carnegie Mellon University
I am a research associate, teaching assistant, and Masters graduate in Artificial Intelligence from Carnegie Mellon University's College of Engineering . My research focuses on using machine learning to process, understand, and make inferences from signals in the world around us, with a particular interest in visual and multimodal representations.
Prior to CMU, I earned a Bachelor's degree with First Class Honors in Software Engineering from The ICT University in Cameroon, graduating first in my department. I currently work with the AI Healthcare Research Lab at CMU, where I work on machine learning methods for understanding cardiac health through the joint analysis of electrocardiogram (ECG) and phonocardiogram (PCG) signals.
Beyond work, I enjoy traveling, reading, and watching documentaries.
Email: bfonya [at] alumni [dot] cmu [dot] edu
Recent News
- 09/2026 – Three (3) co-authored papers accepted at WiML @ NeurIPS 2026
- 09/2026 – Reviewing for Global South AI @ NeurIPS 2026, happening in Sydney, Australia.
- 09/2026 – Our project idea "Nkata" made top 2 and won USD 50,000 seed at the 2026 Digital Humanism Innovation Bootcamp
- 08/2026 – One paper accepted for MICCAI 2026, AFRICAI workshop happening in strasbourg, France.
- 07/2026 – Accepted for the 2nd African Digital Humanism Summer School 2026, Accra, Ghana
- 07/2026 – Attending Deep Learning Indaba 2026
- 06/2026 – Attended The AFRETEC 2026 Bioinformatics and AI Bootcamp, Dakar, Senegal
- 05/2026 – Graduated from Carnegie Mellon University with a Masters degree in Artificial Intelligence.
- 01/2026 – One paper accepted for Oral presentation at IEEE/CVF WACV 2026 workshop, Tucson, Arizona.
- 01/2026 – Joined CMU's (18-662) Principles and Engineering Applications of AI as Graduate TA for Spring 2026.
- 01/2026 – Joined CMU's (18-661) Introduction to Machine Learning for Engineers as Graduate TA for Spring 2026.
- 12/2025 – Featured by Carnegie Mellon University for research journey to China. Read here
- 09/2025 – Started as Graduate TA for (18-751) Applied Stochastic Processes, Fall 2025.
- 07/2025 – Joined Autonomous Intelligence Lab as research intern at Westlake University, China.
- 06/2025 – Paper accepted at European Public Health Conference 2025, Helsinki, Finland.
- 05/2025 – Visited University of Cape Town to explore AI research opportunities.
Research
I am committed to research that ensures AI benefits society, specifically in healthcare. I focus on developing efficient deep learning models for computer vision applications with particular interest in medical imaging and analysis.
Zero-Shot Neural Priors for Generalizable Cross-Subject and Cross-Task EEG Decoding
Baimam Boukar, *Brandone Fonya, Nchofon Tagha, Pauline Nyaboe
A zero-shot EEG decoding framework that learns subject and task-invariant neural priors from large-scale HBN data, enabling robust cross-subject generalization without calibration.
C-BiJEPA: Complementary Bidirectional Joint-Embedding Predictive Learning for Structured Image Representation Learning
*Brandone Fonya, Prasenjit Mitra
Bidirectional self-supervised representation learning with joint-embedding predictive architectures for learning robust representations from unlabeled data.
Preprocessing as Prior: Rethinking Self-Supervised Representation Learning in Cardiac Sound Classification
Mona Aman, Godbright Nixon Uiso, *Brandone Fonya, John Bosco Gachomba Thuo, Maurine Wanjiku Gatimu, Carine Mukamakuza
An empirical study showing how signal preprocessing can act as an implicit prior in self-supervised learning for cardiac sound classification.
Optimizing healthcare facility distribution in Rwanda: a data-driven approach
*Brandone Fonya, Irene Busah, Michaella Rugumbira, Nchofon Tagha, Emily Aiken
Analyzed health facility distribution in Rwanda using geospatial mapping and ML to propose equitable resource allocation based on disease prevalence.
MedBLIPNet3D: Text Prompt-Guided Vision-Language Model for 3D MRI Prostate Segmentation
*Brandone Fonya, Kaicheng Yu
Novel framework for text prompt-guided 3D medical image segmentation using cross-fusion of visual and text encodings.
Robust Non-Invasive Tuberculosis Triage Using Audio Embeddings from Solicitated Cough Sounds
Timothy Belekollie1, *Brandone Fonya, Edwin Mugume, Conrad Tucker, [...].
Audio-based TB screening using pretrained foundation models achieving AUC of 1.000, optimized for mobile edge inference.
CAM-FD: Improving Adversarial Robustness without Sacrificing Generalization
*Brandone Fonya, Denis Musinguzi, Prasenjit Mitra
Curriculum Adversarial Mixup with Feature Denoising framework for increasing robustness while maintaining generalization.
Uncertainty-Aware Autonomous Driving in African Cities
Victor Miene, *Brandone Fonya, Joshua Momo, Ozan Tonguz
Modeling pedestrian behaviors in unstructured urban environments using ConvLSTM, enabling behavioral planning for autonomous vehicles.
Teaching & Service
Carnegie Mellon University
(18-661) Introduction to Machine Learning for Engineers - Graduate TA (Spring 2026)
(18-662) Principles and Engineering Applications of AI - Graduate TA (Spring 2026)
(18-751) Applied Stochastic Processes - Graduate TA (Fall 2025, Fall 2026)
Service
Conference Reviewer, Applied Machine Learning Days (AMLD) Africa 2026
IEEE Student Member (2024 - Present)