Our NeuroPupil paper is out
- 10 hours ago
- 1 min read
Excited to share our new bioRxiv preprint:
“NeuroPupil: A generalization-first framework for scalable and biologically informative cross-species pupillometry”
In this work, we developed NeuroPupil, a deep learning framework for scalable and biologically informative pupil tracking across mice and humans.
We systematically benchmarked training strategies and architectures across diverse behavioral conditions and disease models, including:
🧠 PTEN-associated autism spectrum disorder (ASD)
🧠 Glioblastoma (GBM)
🧠 Multiple sclerosis (MS)
👁️ Pediatric strabismus patients
Our findings show that subtle improvements in pupil tracking precision can significantly impact downstream neural decoding, brain-state prediction, and disease-related classification.
A major collaborative effort at the intersection of neuroscience, AI, behavior, and neurotechnology.
Comments