Co-occurring keywords
Papers
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
NIPS 2024
You Only Look Around: Learning Illumination-Invariant Feature for Low-light Object Detection
NIPS 2024
Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers
NIPS 2024
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
NIPS 2024
Where Do Large Learning Rates Lead Us?
NIPS 2024