3 papers
cs.LG2026
Revisiting the Platonic Representation Hypothesis: An Aristotelian View
Fabian Gröger, Shuo Wen, Maria BrbiÄ
The Platonic Representation Hypothesis suggests that representations from neural networks are converging to a common statistical model of reality. We show that the existing metrics…
cs.LG2026
HeurekaBench: A Benchmarking Framework for AI Co-scientist
Siba Smarak Panigrahi, Jovana VidenoviÄ, Maria BrbiÄ
LLM-based reasoning models have enabled the development of agentic systems that act as co-scientists, assisting in multi-step scientific analysis. However, evaluating these systems…
cs.LG2025
Weak-to-Strong Generalization under Distribution Shifts
Myeongho Jeon, Jan Sobotka, Suhwan Choi +1
As future superhuman models become increasingly complex, accurately supervising their behavior may exceed human capabilities. Recent works have demonstrated that in such scenarios,…