Matthias Bethge

Accurate, reliable and fast robustness evaluation

2019 · 50 Zit. · MPG.PuRe (Max Planck Society)

Wu's Method can Boost Symbolic AI to Rival Silver Medalists and AlphaGeometry to Outperform Gold Medalists at IMO Geometry

2024 · 1 Zit. · arXiv (Cornell University)

Mapping Post-Training Forgetting in Language Models at Scale

2025 · 0 Zit. · ArXiv.org

PostTrainBench: Can LLM Agents Automate LLM Post-Training?

2026 · 0 Zit. · arXiv (Cornell University)

Great Models Think Alike and this Undermines AI Oversight

2025 · 0 Zit. · ArXiv.org

Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation

2025 · 0 Zit. · ArXiv.org