Zacharie Rodiere
Neural Decoding & Real-Time ML Systems
I design and implement machine learning systems for neural data, with a focus on transformer-based architectures, contrastive representation learning, and deployment-oriented inference pipelines.
My recent work explores seizure onset zone localization from intracranial EEG (SEEG), emphasizing cross-patient generalization and low-latency inference.
I grew up in a small town in France, trained as an electrical and computer engineer, and am currently pursuing a Master's in Electrical and Computer Engineering at Georgia Tech.
Selected Work
Two-Stage Spatio-Temporal SEEG Modeling
Transformer-based neural decoding with contrastive pre-training and cross-patient generalization.
Technical Write-Up | Workshop Paper (GSP 2025)
Transformer-based neural decoding with contrastive pre-training and cross-patient generalization.
Technical Write-Up | Workshop Paper (GSP 2025)