Jiangyong Huang

question answering (2) vision-language model (2) scene understanding (1) object recognition (1) visual question answering (1) 3d vision (1) policy learning (1) visual grounding (1) embodied ai (1) continuous state (1) expert demonstration (1) situated reasoning (1) vision language (1) 3d vision-language (1) object-centric evaluation (1) chain of analysis (1) language-grounded task learning (1) benchmark evaluation (1) language-conditioned manipulation (1) sim-to-real transfer (1)