Chenglin Wu

large language model (3) semantic segmentation (1) simulated annealing (1) multi-task learning (1) information bottleneck (1) object detection (1) self-supervised learning (1) in-context learning (1) question answering (1) code generation (1) incremental learning (1) network pruning (1) neural architecture search (1) joint learning (1) image segmentation (1) model convergence (1) prompt optimization (1) retrieval-augmented generation (1) referring expression comprehension (1) deep reinforcement learning (1)