Max Staats

According to our database, Max Staats authored at least 7 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of six.
• Erdős number of six.

2026

Noise and Information in Deep Learning: A Statistical Physics Perspective on Learning and Neural Representations.

Max Staats

PhD thesis, 2026

2025

Small Singular Values Matter: A Random Matrix Analysis of Transformer Models.

Max Staats, Matthias Thamm, Bernd Rosenow

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Enhancing Noise-Robust Losses for Large-Scale Noisy Data Learning.

Max Staats, Matthias Thamm, Bernd Rosenow

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024

Locating Information in Large Language Models via Random Matrix Theory.

Max Staats, Matthias Thamm, Bernd Rosenow

CoRR, 2024

2023

Reevaluating Loss Functions: Enhancing Robustness to Label Noise in Deep Learning Models.

Max Staats, Matthias Thamm, Bernd Rosenow

CoRR, 2023

2022

Boundary between noise and information applied to filtering neural network weight matrices.

Max Staats, Matthias Thamm, Bernd Rosenow

CoRR, 2022

Random matrix analysis of deep neural network weight matrices.

Matthias Thamm, Max Staats, Bernd Rosenow

CoRR, 2022