Andreas Kirsch

According to our database, Andreas Kirsch authored at least 6 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Evaluating the Robustness of Chinchilla Compute-Optimal Scaling.

Rylan Schaeffer, Noam Levi, Andreas Kirsch, Theo Guenais, Brando Miranda, Elyas Obbad, Sanmi Koyejo

CoRR, September, 2025

When three experiments are better than two: Avoiding intractable correlated aleatoric uncertainty by leveraging a novel bias-variance tradeoff.

Paul Scherer, Andreas Kirsch, Jake P. Taylor-King

CoRR, September, 2025

Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs.

Nguyen Nhat Minh, Andrew Baker, Clement Neo, Allen G. Roush, Andreas Kirsch, Ravid Shwartz-Ziv

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

All models are wrong, some are useful: Model Selection with Limited Labels.

Patrik Okanovic, Andreas Kirsch, Jannes Kasper, Torsten Hoefler, Andreas Krause, Nezihe Merve Gürel

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

(Implicit) Ensembles of Ensembles: Epistemic Uncertainty Collapse in Large Models.

Andreas Kirsch

CoRR, 2024

Min P Sampling: Balancing Creativity and Coherence at High Temperature.

Minh Nguyen, Andrew Baker, Andreas Kirsch, Clement Neo

CoRR, 2024