Kuan Fang

3d reconstruction (2) affordance prediction (2) vision-language model (2) multi-task learning (2) robotic manipulation (2) offline reinforcement learning (2) goal-conditioned policy (2) scene understanding (1) domain generalization (1) semi-supervised learning (1) imitation learning (1) variational inference (1) zero-shot learning (1) hierarchical planning (1) video understanding (1) action recognition (1) feature embedding (1) visual reasoning (1) visual navigation (1) attention mechanism (1)