Ziqin Wang

multi-agent reinforcement learning (1) semantic segmentation (1) self-attention mechanism (1) imitation learning (1) preference learning (1) multimodal learning (1) point cloud (1) 3d vision (1) multi-modal learning (1) policy learning (1) human-object interaction (1) 3d scene understanding (1) humanoid robot (1) motion detection (1) pyramid structures (1) robot manipulation (1) salient object detection (1) cooperative learning (1) multimodal large language model (1) retrieval augmented generation (1)