Pre-Training Buys Better Robustness and Uncertainty Estimates (ICML 2019)

“SURE: SUrvey REcipes for building reliable and robust deep networks” (CVPR 2024) & (ECCV 2024 OOD-CV Challenge Winner)

Effective and Robust Adversarial Training Against Data and Label Corruptions

This project quantifies the geometric and structural "break-point" of LLM representations under data corruption. Using Intrinsic Dimension and CKA mapping, it identifies the exact transformer layers where noise destroys semantic alignment and triggers Uncertainty Calibration collapse.

This application securely performs deletion by overwriting image files with random data, making them unrecoverable. It’s ideal for safely deleting non-sensitive files.

Node-based glitch art application for building image processing pipelines