2 papers
cs.LG2026
CCAR: Intrinsic Robustness as an Emergent Geometric Property
Akash Samanta, Manish Pratap Singh, Debasis Chaudhuri
Standard supervised learning optimizes for predictive accuracy but remains agnostic to the internal geometry of learned features, often yielding representations that are entangled…
cs.LG2025
Self Distillation via Iterative Constructive Perturbations
Maheak Dave, Aniket Kumar Singh, Aryan Pareek +3
Deep Neural Networks have achieved remarkable achievements across various domains, however balancing performance and generalization still remains a challenge while training these n…