11 citations · 11 across the 2 of their papers we have counts for
2 papers
cs.AI2026
Belief or Circuitry? Causal Evidence for In-Context Graph Learning
Katharine Kowalyshyn, Timothy Duggan, Daniel Little +1
How do LLMs learn in-context? Is it by pattern-matching recent tokens, or by inferring latent structure? We probe this question using a toy graph random-walk across two competing g…
cs.LG2011★ 11 cited
Learning in embodied action-perception loops through exploration
Daniel Y. Little, Friedrich T. Sommer
Although exploratory behaviors are ubiquitous in the animal kingdom, their computational underpinnings are still largely unknown. Behavioral Psychology has identified learning as a…