Siqi Wang

Reinforcement Learning (1)

reinforcement learning (3) neural network optimization (2) scaling law (2) autonomous driving (2) image classification (2) unsupervised learning (2) transfer learning (1) optimal transport (1) representation learning (1) object detection (1) 3d occupancy prediction (1) frame interpolation (1) self-supervised learning (1) knowledge distillation (1) hyperparameter optimization (1) model architecture (1) depth estimation (1) matrix factorization (1) chain-of-thought reasoning (1) domain adaptation (1)