Run Peng
Run Peng
Home
Publications
CV
Light
Dark
Automatic
Embodied AI
Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models
Responsible for designing and implementing all ten tasks on minigrid; Actively Contributed to test LLM’s understanding on situated theory of mind, unveiling its lack of ability to correctly reason the theory of mind
PDF
Code
Dataset
Post
Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models
Theory of Mind, Large Language Models, Mental States
Ziqiao Ma
,
Jacob Sansom
,
Run Peng
,
Joyce Chai
PDF
Cite
Code
Dataset
Project
Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation
Interactive object detection, personalization in robotics, LLM based navigation
Yinpei Dai
,
Run Peng
,
Sikai Li
,
Joyce Chai
PDF
Cite
Exploring LLM in Intention Modeling for Human-Robot Collaboration
Humans develop Theory of Mind (ToM) at a young age - the ability to understand that others have intents, beliefs, knowledge, skills, etc. that may differ from our own. Modeling others’ mental states plays an important role in human-human communication and collaborative tasks.
Slides
Post
Cite
×