2 papers
cs.LG2026
Supervised Distributional Reduction via Optimal Transport and Dependence Maximization
Sai-Aakash Ramesh, Archit Sood, Andrew Corbett +1
Learning representations that capture both intrinsic data geometry and target-relevant structure remains a fundamental challenge, particularly in settings where data reduction must…
cs.AI2026
Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models
Andrew Corbett, Archit Sood, Anna Tzatzopoulou +2
Recent work on recursive architectures has shown that tiny neural networks can be surprisingly powerful on structured reasoning tasks. The trick is to model reasoning trajectories…