Giovanni Iacca

reinforcement learning (2) adversarial learning (1) robotic manipulation (1) transfer learning (1) entropy minimization (1) curriculum learning (1) confidence calibration (1) test-time adaptation (1) continuous control (1) model pruning (1) reward function (1) linear classifier (1) diffusion model (1) decision tree (1) vision language model (1) parameter efficient fine-tuning (1) mixture of expert (1) vision-language model (1) sparse activation (1) model generalization (1)