← Search

Mirko Thalmann

2 accepted papers

2025

Building, Reusing, and Generalizing Abstract Representations from Concrete Sequences

ICLR 2025poster

Humans excel at learning abstract patterns across different sequences, filtering out irrelevant details, and transferring these generalized concepts to new sequences. In contrast, many sequence learning models lack the ability to abstract, which leads to memory inefficiency and poor transfer. We int…

Cited by 0SourcePDFScholar
2024

Human-like Category Learning by Injecting Ecological Priors from Large Language Models into Neural Networks

ICML 2024poster

Ecological rationality refers to the notion that humans are rational agents adapted to their environment. However, testing this theory remains challenging due to two reasons: the difficulty in defining what tasks are ecologically valid and building rational models for these tasks. In this work, we d…

Cited by 2SourcePDFScholar