Richard Freinschlag — accepted AI-conference papers

2026

Symbol-Equivariant Recurrent Reasoning Models

Richard Freinschlag, Timo Bertram, Erich Kobler, Andreas Mayr, Günter Klambauer

ICML 2026poster

Reasoning problems such as Sudoku and ARC-AGI remain challenging for neural networks. Recurrent Reasoning Models (RRMs), including Hierarchical Reasoning Models (HRM) and Tiny Recursive Models (TRM), offer a compact alternative to large language models, but currently handle symbol symmetries only im…

Cited by 0 Source ↗Scholar ↗

2025

pLSTM: parallelizable Linear Source Transition Mark networks

Korbinian Pöppel, Richard Freinschlag, Thomas Schmied, Wei Lin, Sepp Hochreiter

NeurIPS 2025poster

Modern recurrent architectures, such as xLSTM and Mamba, have recently challenged the Transformer in language modeling. However, their structure constrains their applicability to sequences only or requires processing multi-dimensional data structures, such as images or molecular graphs, in a pre-…

Cited by 0 Source ↗code ↗Scholar ↗