3 papers
cs.LG2026
Float8@2bits: Entropy Coding Enables Data-Free Model Compression
Patrick Putzky, Martin Genzel, Mattes Mollenhauer +3
Post-training compression is currently divided into two contrasting regimes. On the one hand, fast, data-free, and model-agnostic methods (e.g., NF4 or HQQ) offer maximum accessibi…
cs.LG2025
Choose Your Model Size: Any Compression of Large Language Models Without Re-Computation
Martin Genzel, Patrick Putzky, Pengfei Zhao +5
The adoption of Foundation Models in resource-constrained environments remains challenging due to their large size and inference costs. A promising way to overcome these limitation…
stat.ML2024
Memorization With Neural Nets: Going Beyond the Worst Case
Sjoerd Dirksen, Patrick Finke, Martin Genzel
In practice, deep neural networks are often able to easily interpolate their training data. To understand this phenomenon, many works have aimed to quantify the memorization capaci…