Leonard Bereska

Identifiers

• name variant Leonard Bereska 0.60 · backfill

Papers (2)

1. Mechanistic Interpretability for AI Safety -- A Review cs.AI · 2024 · author #1
2. Unsupervised Part-Based Disentangling of Object Shape and Appearance cs.CV · 2019 · author #2

Mentions

• 2404.14082 #1 · arxiv_oai · confidence 0.70 Leonard Bereska

Frequent Coauthors

• Bj\"orn Ommer 1 shared papers
• Dominik Lorenz 1 shared papers
• Efstratios Gavves 1 shared papers
• Timo Milbich 1 shared papers