Home
People
Research
Publications
Teaching
Demos
Resources
Join Us
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
«
»
Cite
×