Pengzhen Ren

robotic manipulation (3) vision-language model (2) robust clustering (2) semantic segmentation (1) pose estimation (1) vision transformer (1) reinforcement learning (1) sim-to-real transfer (1) model architecture (1) spectral clustering (1) graph learning (1) computer vision (1) noise suppression (1) hierarchical planning (1) subspace learning (1) self-attention mechanism (1) object detection (1) cross-modal learning (1) dimensionality reduction (1) multi-view clustering (1)