4 papers
Word Class Representations Spontaneously Emerge from Successor Representations Trained on Natural Language
Mathis Immertreu, Achim Schilling, Thomas Kinfe +1
Language models are typically trained to predict the next token in a sequence. Here, we explore an alternative predictive principle from reinforcement learning: Successor Represent…
Neuroscience-Inspired Analyses of Visual Interestingness in Multimodal Transformers
Mathis Immertreu, Fitim Abdullahu, Thomas Kinfe +3
Human attention is the gateway to conscious perception, memory and decision-making. However, its role in modern transformer models remains largely unexplored. As these systems incr…
Fourier Neural Operators for Two-Phase, 2D Mold-Filling Problems Related to Metal Casting
Edgard Moreira Minete, Mathis Immertreu, Fabian Teichmann +1
We formulate mold filling in metal casting as a 2D neural operator learning problem that maps geometry and boundary data on an unstructured mesh to time resolved flow quantities, r…
Probing for Consciousness in Machines
Mathis Immertreu, Achim Schilling, Andreas Maier +1
This study explores the potential for artificial agents to develop core consciousness, as proposed by Antonio Damasio's theory of consciousness. According to Damasio, the emergence…