Joyce Chai

Multi-Object Hallucination in Vision-Language Models
Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use
3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination
LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent
SEAGULL: An Embodied Agent for Instruction Following through Situated Dialog
DANLI: Deliberative Agent for Following Natural Language Instructions