Piotr Miłoś

continual learning (3) reinforcement learning (2) large language model (2) long context (2) transfer learning (2) contrastive learning (2) context utilization (2) continuous control (2) catastrophic forgetting (1) in-context learning (1) representation learning (1) information retrieval (1) out-of-distribution generalization (1) data representation (1) attention mechanism (1) puzzle solving (1) gradient descent (1) continual reinforcement learning (1) best-first search (1) signaling games (1)