Wei Liang

multimodal learning (4) vision-language navigation (4) embodied navigation (3) diffusion model (3) 3d scene understanding (3) few-shot learning (2) scene-aware generation (2) agent navigation (2) vision-language model (2) convolutional neural network (2) human motion generation (2) frontier exploration (2) agent system (2) scene understanding (2) visual grounding (2) active learning (2) visual reasoning (2) cognitive modeling (1) bayesian inference (1) pose estimation (1)