Jesse Thomason

When people query Vision-Language Models (VLMs) but cannot see the accompanying visual context (e.g. for blind and low-vision users), augmenting VLM predictions with natural language explanations can signal which model predictions are reliable. However, prior work has found that explanations can...

Using LLMs not to predict plans but to formalize an environment into the Planning Domain Definition Language (PDDL) has been shown to improve performance and control. While most existing methodology only applies to fully observable environments, we adapt to the more realistic and challenging part...

While word embeddings derive meaning from co-occurrence patterns, human language understanding is grounded in sensory and motor experience. We present \mathit{SENSE} ( \textbf{S} ensorimotor \textbf{E} mbedding \textbf{N} orm \textbf{S} coring \textbf{E} ngine), a learned projection model that pr...