Authors

Samuel Horváth

Publications 2

Preprint Open access

NeuralZip: Reusable Setup for Fast Lossless Compression

Martín Bravo, Samuel Horváth, Gonzalo Navarro et al. · 2026

Lossless compression can reduce the storage and movement of model weights without changing their floating-point values, but repeated statistical analysis and code construction add computational overhead. We study whether the statistical structure of exponents can be prepared once and reused. For this, we introduce Neur …

Preprint Open access

LionMuon: Alternating Spectral and Sign Descent for Efficient Training

Arman Bolatov, Artem Riabinin, Nikita Kornilov et al. · 2026

Pretraining a language model takes enormous compute, and the right optimizer can save a good part of it. Muon's spectral step gives a stronger direction than a sign step, but it is expensive. Every step runs Newton-Schulz iterations on the full matrix and, in distributed training, an extra all-reduce. Sign steps, as in …

Co-authors