Wei Dai

distributed optimization (2) model parallel (2) legal judgment (2) speech enhancement (2) feature selection (2) neural network (2) asynchronous computation (2) prison term prediction (2) anomaly detection (1) data augmentation (1) reward modeling (1) information retrieval (1) multimodal learning (1) language model alignment (1) unsupervised learning (1) machine translation (1) model alignment (1) attention mechanism (1) reinforcement learning (1) reinforcement learning from human feedback (1)