Currently · Planning CV4CHL at CVPR 2026
Pediatric AI Research Lab

Trustworthy AI for the smallest patients.

PediaMed AI is a pediatric AI research lab building interpretable vision and multimodal models for early detection and clinician-readable explanations.

Illustrative pediatric pose-overlay artifactA diagrammatic infant pose overlay with 15 landmark points and per-point confidence rings, layered over light growth-chart percentile bands. The visual illustrates how AggPose attaches calibrated confidence to each landmark; it is not a live model output.P3P15P50P85P97CONFIDENCE ENCODINGLOWER → WIDER RING15 LANDMARKSHEADTORSOLSHRSHLELRELLWRRWR
8
Publications & preprints
3
Research themes
4
Partner institutions
2
Workshops

Pediatric medicine deserves the same generation of AI tools as oncology and radiology — designed for the bodies, faces, and rare diseases of children.

We are building them with clinicians, for children.

  • — Interpretable

    Every prediction comes with a faithful, clinician-readable explanation. No black boxes at the bedside.

  • — Pediatric-first

    Models trained, validated, and benchmarked on children — not adapted from adult datasets after the fact.

  • — Open by default

    Datasets, weights, and methods released openly. Knowledge belongs to the field.

From question to release.

  1. — 01 / Define

    A pediatric clinical question, scoped with hospital and university collaborators.

  2. — 02 / Build

    Vision and multimodal models with reference implementations and training recipes.

  3. — 03 / Validate

    Calibration error, robustness checks, and — where applicable — clinician review.

  4. — 04 / Release

    Datasets, weights, and methods released openly. Knowledge belongs to the field.

Open to collaboration

Clinicians, hospitals, and ML researchers: let's build pediatric AI together.