conftrace_

Michael Aerni

4 papers · 2021–2026 · 3 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓

🌍 Conference Polyglot (2) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (7)

Conferences

ICLR (2) ACL (1) NIPS (1)

Top co-authors

Konstantin Donhauser (2) Fanny Yang (2) Javier Rando (2) Florian Tramer (2) Clément Charmillot (1) Martin Rajman (1) Jiaming Jiang (1) Lukas Drescher (1) Ido Hakimi (1) Kaustubh Ponkshe (1)

Keywords

robust overfitting (1) robust generalization (1) ridge regularization (1) multilingual language model (1) max-margin classifier (1) large language model (1) responsible artificial intelligence (1) min-norm interpolator (1) data compliance (1) goldfish objective (1)

Papers

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments ACL 2026 Measuring Non-Adversarial Reproduction of Training Data in Large Language Models ICLR 2025 Strong inductive biases provably prevent harmless interpolation ICLR 2023 Interpolation can hurt robust generalization even when there is no noise NIPS 2021