Ines Montani
where else to find them
website:https://ines.io
github:ines
bluesky:inesmontani.bsky.social
mastodon:@ines@sigmoid.social
linkedin:inesmontani
speakerdeck:inesmontani
youtube:c/ExplosionAI
what they talk about
all 7 in the filters
where they keep going back
- PyData London3 editions2024–2026
all 6 in the filters
on a stage with
- Alexander Beckonce
- Alexander CS Hendorfonce
- Ryan Wesslenonce
all 4 in the filters
who talks about the same things
- Sebastian Neubauer4 talks
- Alexander CS Hendorf25 talks
- Tereza Iofciu15 talks
- Larissa Haas4 talks
- Serhii Sokolenko5 talks
- Juan Luis Cano Rodríguez11 talks
| title | conference | date |
|---|---|---|
| Vibe NLP for Applied NLP | PyData London 2026 | 2026-06-05 |
Claims a concrete workflow: use LLMs to write reusable scripts and training data so runtime inference uses small private classifiers that are faster and… | ||
| Conquering PDFs- document understanding beyond plain text | PyData London 2025 | 2025-06-06 |
Claims that PDFs are a bad source of truth and that extracting a unified structured format first makes document pipelines manageable. Uses Dockling plus a… | ||
| Conquering PDFs: document understanding beyond plain text | PyCon DE & PyData 2025 | 2025-04-23 |
A practical wrapper integrates Dockling with spaCy to extract text plus layout spans and bounding boxes from PDFs, feed that Dockling document into existing… | ||
| AI in Reality Fireside Chat: Enterprise AI & Open‑Source Innovation | PyCon DE & PyData 2025 | 2025-04-23 |
Covers concrete enterprise moves: Merck runs a four‑year AI program for 63,000 employees, prototypes LLMs, then abandons an internal clone for a partnership to… | ||
| Reality is not an end-to-end prediction problem | dotAI 2024 | 2024-10-17 |
Argues that prompts alone fail for production systems and shows a concrete pipeline: use spaCy llm and Prodigy for LLM-assisted annotation, transfer-learn… | ||
| Keynote: Applied NLP in the age of Generative AI | PyData Amsterdam 2024 | 2024-09-18 |
Describes concrete workflows and outcomes: uses spaCy and Prodigy for semi-automated annotation, applies transfer learning to replace LLM prototypes with small… | ||
| A practical guide to human-in-the-loop distillation | PyData London 2024 | 2024-06-14 |
Describes a concrete workflow: prompt a large LLM, parse its text to structured output, have humans correct the outputs with human-in-the-loop distillation… | ||
| The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs | PyCon Italia 2024 | 2024-05-22 |
Argues open-source pipelines win over pure scale by showing concrete tooling and a clear workflow: use spaCy and Prodigy plus a large generative model to… | ||
| Half hour of labeling power: Can we beat GPT? | PyData NYC 2023 | 2023-11-01 |
Claims that LLMs are best used at development time to pre‑annotate and speed dataset creation, then fine‑tune smaller task‑specific models to match or beat… | ||
| nothing matches | ||