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.RO2026
The Price Is Not Right: Neuro-Symbolic Methods Outperform VLAs on Structured Long-Horizon Manipulation Tasks with Significantly Lower Energy Consumption
Timothy Duggan, Pierrick Lorang, Hong Lu +1
Vision-Language-Action (VLA) models have recently been proposed as a pathway toward generalist robotic policies capable of interpreting natural language and visual inputs to genera…