We have 3 of 6 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
This work shows that successful grasp sets exhibit heterogeneous and reproducible connectivity structure across objects, and introduces a connectivity-aware sampling strategy that incrementally explores the currently observed grasp space by prioritizing potential bridges between components, structural frontiers, bounda...
This work proposes FlowLess-R, a representation-space regularization method that constrains replay representations relative to stored references while allowing continued learning and introduces representation flux, a geometric measure of sample-level representation displacement across training.
It is found that dimensionality collapse consistently precedes the onset of grokking in all evaluated settings, and Geometric Dimensionality Regularization (GeomDR), a simple spectral regularizer that modifies the effective dimensionality of hidden representations during training is introduced.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
