6 papers
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, ``…
RePAIR: Predictive Self-Supervised Representation Learning in Chess
Christoph Koller, Johannes Fürnkranz, Timo Bertram
In this paper, we introduce Representation Prediction via Autoencoding using Iterative Refinement (RePAIR) - a novel self-supervised representation learning architecture that synth…
Toxicity in Twitch Chats: An LLM-Based Analysis Across Gaming Communities
Ronja Fuchs, Florian Rupp, Timo Bertram +2
Toxicity in online gaming communities remains a persistent challenge, manifesting across genres, platforms, and player interactions. While much research is focused on in-game toxic…
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…
UrzaGPT: LoRA-Tuned Large Language Models for Card Selection in Collectible Card Games
Timo Bertram
Collectible card games (CCGs) are a difficult genre for AI due to their partial observability, long-term decision-making, and evolving card sets. Due to this, current AI models per…
Deceptive Game Design? Investigating the Impact of Visual Card Style on Player Perception
Leonie Kallabis, Timo Bertram, Florian Rupp
The visual style of game elements considerably contributes to the overall experience. Aesthetics influence player appeal, while the abilities of game pieces define their in-game fu…