Suraj Srinivas

adversarial robustness (2) neural network (2) model interpretability (2) representation learning (1) transfer learning (1) domain adaptation (1) model robustness (1) embedding learning (1) feature disentanglement (1) knowledge distillation (1) batch normalization (1) multimodal learning (1) model architecture (1) explainable ai (1) concept representation (1) adversarial training (1) feature attribution (1) model editing (1) function approximation (1) sparse recovery (1)