Irina Vidal Migallón
where else to find them
no profile links on file
what they talk about
where they keep going back
- PyData Global2 editions2020–2024
- PyData Berlin2 editions2017–2018
on a stage with
never shared a talk
who talks about the same things
- Tess Ferrandez-Norlander24 talks
- Thomas Endres17 talks
- Katharine Jarmul25 talks
- Jonas Mayer13 talks
- Rishabh Misra5 talks
- Martin Förtsch17 talks
| title | conference | date |
|---|---|---|
| Trustworthy LLMs: Vibe checks are not all you need | PyData Global 2024 | 2024-12-03 |
Claim: eyeballing LLM outputs is insufficient; set up an automated evaluation pipeline that measures task performance plus robustness, hallucinations, data… | ||
| Visual data abundant relevant labelled cheap Pick two | PyData Global 2020 | 2020-11-11 |
Describes concrete tools and limits: use transfer learning, classic augmentations and use adversarial augmentations in both training and testing to probe… | ||
| When to go deep in Computer Vision... and how | PyData Berlin 2018 | 2018-07-06 |
Decide by specifics: a quick OpenCV plugin for Unity baseline often runs on phone/hololens and uses cascade detectors for face/hand detection; measure against… | ||
| Deep Learning for detection on a phone | PyData Berlin 2017 | 2017-06-23 |
Pipeline shows how a detector gets from prototype to phone: configuration-driven deployment file, model definition converted to convolutional-only layers… | ||
| nothing matches | ||