Bernhard Schölkopf

ELLIS Institute Tübingen, Max Planck Institute for Intelligent Systems, Tübingen, Germany, ELLIS Institute Tübingen, Tübingen, Germany

Mila

Papers on Lattice

Total citations

Topics

h-index

Research focus

Constitutional AI & AI Ethics (1)Eval Frameworks & Benchmarks (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Y. Bengio (1)Stephen Clare (1)Carina Prunkl (1)Maksym Andriushchenko (1)

Papers (1)

Dec 7, 2025

MilaDec 7, 2025·also BAIR, MIT CSAIL, Stanford HAI, ELLIS +5

International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management

Despite progress in AI safety, it's still largely unknown how effective current safeguards are at preventing AI harms, and their effectiveness varies wildly.

Y. Bengio, Stephen Clare, Carina Prunkl +34

Constitutional AI & AI Ethics Eval Frameworks & Benchmarks Red-Teaming & Adversarial Robustness

Search

Bernhard Schölkopf

Research focus

Frequent co-authors

Papers (1)