YiDing Jiang

representation learning (2) implicit neural representation (2) reinforcement learning (2) multi-task learning (2) neural network (2) attention mechanism (1) out-of-distribution generalization (1) epistemic uncertainty (1) permutation equivariance (1) instruction following (1) model architecture (1) language grounding (1) compositional generalization (1) hierarchical reinforcement learning (1) distribution shift (1) maximum likelihood (1) weight sharing (1) temporal abstraction (1) prompt-based learning (1) model selection (1)