Loading activity…
@baophamhq
PhD Student at @rpi interning at @NASA. I work on energy-based modeling and genAI. Spent time @AMD and @IBMResearch.
AI
One team likens diffusion models to associative memory; another says its scaling law predicts when memorization begins.
AI
The author reports that as the model enters generalization, its token recovery rate after perturbation improves on unseen test examples and worsens on training examples.