Get started
Author

Alexander Hägele

Observed name: Hägele, Alexander
OpenAlex ID: A5098954170
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments
2026 · Alejandro Hernández-Cano, Alexander Hägele, et al. · Annual Meeting of the Association for Computational Linguistics (ACL) · 17
PDF
Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations
2024 · Alexander Hägele, Elie Bakouch, et al. · neural information processing systems · 2
PDF
The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?
2026 · Hägele, Alexander, Gema, Aryo Pradipta, et al. · arXiv (Cornell University) · 1
The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training
2025 · Schaipp, Fabian, Hägele, Alexander, et al. · arXiv (Cornell University) · 1
PDF
Apertus 1.5: From Open Text Models to Open Multimodal Reasoners
2026 · Apertus, Project, :, et al. · arXiv (Cornell University)
PDF
Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors
2026 · Hägele, Alexander, Hernández-Cano, Alejandro, et al. · arXiv (Cornell University)
PDF
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments
2026 · Association for Computational Linguistics 2026, AlKhamissi, Badr, et al. · Underline Science Inc.
Inverse Scaling in Test-Time Compute
2025 · Gema, Aryo Pradipta, Hägele, Alexander, et al. · arXiv (Cornell University)
PDF
Works count: 9
Citation count: 21
H-index: 2
I10-index: 1
Year
Topic
Type