3 papers
cs.CV2026
Zero-Ablation Overstates Register Content Dependence in DINO Vision Transformers
Felipe Parodi, Jordan Matelsky, Melanie Segado
Zero-ablation -- replacing token activations with zero vectors -- is widely used to probe token function in vision transformers. Register zeroing in DINOv2+registers and DINOv3 pro…
cs.AI2025
Grounding Intelligence in Movement
Melanie Segado, Felipe Parodi, Jordan K. Matelsky +3
Recent advances in machine learning have dramatically improved our ability to model language, vision, and other high-dimensional data, yet they continue to struggle with one of the…
cs.LG2024
Empirical influence functions to understand the logic of fine-tuning
Jordan K. Matelsky, Lyle Ungar, Konrad P. Kording
Understanding the process of learning in neural networks is crucial for improving their performance and interpreting their behavior. This can be approximately understood by asking…