Songlin Wei

Artificial Intelligence (3) Computer Vision (3) Robotics (3) Analysis (3) Capabilities (3) Core AI (3) Deep Learning (1) Machine Learning (1) Reinforcement Learning (1) Application Areas (1) Applications (1) Architectures (1) Learning Types (1)

reinforcement learning (1) imitation learning (1) sim-to-real transfer (1) robot navigation (1) multimodal learning (1) video understanding (1) synthetic data generation (1) diffusion model (1) synthetic data (1) end-to-end learning (1) vision-language model (1) articulated object (1) vision-language-action model (1) natural language instruction (1) denoising diffusion probabilistic model (1) embodied navigation (1) vision language action (1) disparity map (1) transparent object (1) language instruction (1)