Author

Piotr Jedryszek

h-index 2 View on Semantic Scholar

We have 1 of 8 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Aug 2026

Efficient Auto-Interpretability of AI Models in Biology

Cross-seed dictionary stability prioritisation finds interpretable latents using about 4.4 times fewer latent evaluations each, and at 5.2 times lower measured cost, while recovering over half of them, and the external check shows the surfaced motifs are significantly enriched for their claimed annotations.

Piotr Jedryszek, Oliver M. Crook · 0 citations