Alexander Hägele's picture

3 1

Alexander Hägele

haeggee

·

https://haeggee.github.io

AI & ML interests

None yet

Recent Activity

upvoted a paper 7 days ago

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

View all activity

Organizations

authored 2 papers 3 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 • 27

authored a paper 9 months ago

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

Paper • 2501.18965 • Published Jan 31 • 7

authored a paper over 1 year ago

Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations

Paper • 2405.18392 • Published May 28, 2024 • 12