Chengcheng Wang

model architecture (2) transformer architecture (1) semi-supervised learning (1) image generation (1) unsupervised pretraining (1) object detection (1) self-supervised learning (1) model pretraining (1) fine-grained classification (1) fine-grained recognition (1) state space model (1) diffusion model (1) hidden state (1) convolutional neural network (1) foundation model (1) latent space (1) mixture of expert (1) inference acceleration (1) expert activation (1) species classification (1)