3 papers
cs.AI2026
G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models
Timo Bertram, Sidhant Bhavnani, Richard Freinschlag +3
In this work, we focus on SE-RRMs, a symbol-equivariant instantiation of RRMs that exhibits improved extrapolation to larger problem sizes. We propose a neuro-symbolic approach, ``…
cs.LG2026
Symbol-Equivariant Recurrent Reasoning Models
Richard Freinschlag, Timo Bertram, Erich Kobler +2
Reasoning problems such as Sudoku and ARC-AGI remain challenging for neural networks. The structured problem solving architecture family of Recurrent Reasoning Models (RRMs), inclu…
cs.LG2026
LaM-SLidE: Latent Space Modeling of Spatial Dynamical Systems via Linked Entities
Florian Sestak, Artur Toshev, Andreas Fürst +3
Generative models are spearheading recent progress in deep learning, showcasing strong promise for trajectory sampling in dynamical systems as well. However, whereas latent space m…