Ebenezer Gelo
Engineer, AI Researcher, Solopreneur and a coffee-fueled code conjurer. I love building things and helping people.
GitHub Activity
831 contributions in the last year
About
Growing up in Hawassa, Ethiopia, my passion for gaming sparked an early fascination with technology, which has since evolved into a focused interest in AI. Currently, I am part of the RAIL Lab, where I focus on safe reinforcement learning, aiming to contribute positively to advancements in the field and the intersection of technology and society.
Updates
Experience
- P
PYGIO
Data Scientist
Working on end-to-end data solutions with a strong focus on data analysis, while also contributing to AI-driven projects where needed. - R
RAIL Lab
Graduate Student
Conducting research at the RAIL Lab (Wits University) focused on safe decision-making in AI agents, with an emphasis on offline RL and feedback-driven behavioral shaping. - E
EPFL
Research Intern
Selected to the highly competitive Summer@EPFL program (1.3% acceptance rate) and worked under the supervision of Prof. Mary-Anne Hartley at EPFL’s LiGHT Lab, exploring prognosis modeling for macroscopic HCC.
Projects
Inferring Prognosis for Macroscopic Hepatocellular Carcinoma
ViewUsing multi-modal deep learning to predict disease progression in Hepatocellular Carcinoma (HCC) patients by integrating clinical data and medical imaging.
Redistribution-based Cost Inference for Safe Offline RL
ViewIntegrating expert feedback into offline RL to enhance decision-making in safety-critical environments while minimizing risks associated with live trials.
Learning World Value Functions(WVFs) without Exploration
ViewExploring how offline RL algorithms learn goal-oriented representations - World Value Functions (WVF), emphasizing the importance of dataset size and diversity.