Nevan Wichers

representation learning (1) reinforcement learning (1) sample efficiency (1) reward modeling (1) policy optimization (1) transfer learning (1) gradient-based optimization (1) video prediction (1) self-supervised learning (1) natural language generation (1) text generation (1) multimodal learning (1) language model evaluation (1) multi-modal learning (1) llm evaluation (1) prompt learning (1) language model (1) adversarial loss (1) reward shaping (1) unsupervised learning (1)