1

Are We There Yet? Learning to Localize in Embodied Instruction Following

Embodied instruction following is a challenging problem requiring an agent to infer a sequence of primitive actions to achieve a goal environment state from complex language and visual inputs. Action Learning From Realistic Environments and …

Experience Grounds Language

Explainable AI as Collaborative Task Solving

Natural Language Interaction with Explainable AI Models

Commonsense Justification for Action Explanation

Language to Action: Towards Interactive Task Learning with Physical Agents

Language to Action: Towards Interactive Task Learning with Physical Agents (Keynote Presentation)

What Action Causes This? Towards Naive Physical Action-Effect Prediction

Interactive Learning of Grounded Verb Semantics towards Human-Robot Communication

Grounded Semantic Role Labeling