Alexander Hägele

haeggee's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 3 papers 2 months ago

Training Dynamics of the Cooldown Stage in Warmup-Stable-Decay Learning Rate Scheduler

Paper • 2508.01483 • Published Aug 2, 2025 • 1

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

Paper • 2509.14233 • Published Sep 17, 2025 • 18

The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?

Paper • 2601.23045 • Published Jan 30

authored 2 papers 9 months ago

BaCaDI: Bayesian Causal Discovery with Unknown Interventions

Paper • 2206.01665 • Published Jun 3, 2022 • 2

Inverse Scaling in Test-Time Compute

Paper • 2507.14417 • Published Jul 19, 2025 • 28

authored a paper about 1 year ago

The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training

Paper • 2501.18965 • Published Jan 31, 2025 • 7

authored a paper almost 2 years ago

Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations

Paper • 2405.18392 • Published May 28, 2024 • 12