Ondrej Bohdal

model merging (4) low-rank adapter (3) large language model (3) parameter-efficient fine-tuning (3) on-device deployment (3) few-shot learning (2) multi-task learning (2) compositional multi-tasking (2) low-rank adaptation (2) on-device inference (2) model compression (2) text summarization (1) gradient-based optimization (1) hyperparameter optimization (1) representation learning (1) pose estimation (1) parameter efficient fine-tuning (1) domain adaptation (1) semantic segmentation (1) transfer learning (1)