self-supervised learning
2 posts
Article
NovaMind ditches SSL loss for probe accuracy
Why pretext loss misleads in self-supervised learning, and how to select hyperparameters and architectures using probing harnesses that actually track quality.
Article
Sub-JEPA tightens the prediction signal
Sub-JEPA is a small loss-side fix to LeCun's world models that consistently improves performance. Here's how it works, where it fails, and why it matters.