activity
20242026
collaborators

11 papers

cs.LG2026

Tydra: An Efficient Hybrid Model for Tabular Data

Mieszko Komisarczyk, Saurabh Mathur, Maurice Kraus +2

Transformer-based tabular foundation models such as TabPFN achieve strong predictive performance but incur quadratic computational cost with context length. On the other hand, subq…

cs.CL2026

A Sovereign, Open-Source Foundation Model for German and English

The Soofi-Team, Soofi-Team, : +31

We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation model for German and English. Its hybrid design activates only 3B…

cs.CL2026

KletterMix: Climbing Toward High-Quality German Pretraining Data - The Full Report

Maurice Kraus, Ruben Härle, Sebastian Sztwiertnia +5

High-quality pretraining data is a central ingredient in modern language models, but German-language resources remain far less developed than their English counterparts: they are o…

cs.LG2026

Recursive Inference Machines for Neural Reasoning

Mieszko Komisarczyk, Saurabh Mathur, Maurice Kraus +2

Neural reasoners such as Tiny Recursive Models (TRMs) solve complex problems by combining neural backbones with specialized inference schemes. Such inference schemes have been a ce…

cs.CL2026

EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection

Christoph Schuhmann, Robert Kaczmarczyk, Gollam Rabby +6

Speech emotion recognition (SER) systems are constrained by existing datasets that typically cover only 6-10 basic emotions, lack scale and diversity, and face ethical challenges w…

cs.LG2025

xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories

Maurice Kraus, Felix Divo, Devendra Singh Dhami +1

Time series data is prevalent across numerous fields, necessitating the development of robust and accurate forecasting models. Capturing patterns both within and between temporal a…