4 papers · 1 filter
Information Routing in Atomistic Foundation Models: How Task Alignment and Equivariance Shape Linear Disentanglement
Joshua Steier
What determines whether a molecular property prediction model organizes its representations so that geometric and compositional information can be cleanly separated? We introduce C…
PAC Guarantees for Reinforcement Learning: Sample Complexity, Coverage, and Structure
Joshua Steier
When data is scarce or mistakes are costly, average-case metrics fall short. What a practitioner needs is a guarantee: with probability at least , the learned policy is $\vare…
When Does Margin Clamping Affect Training Variance? Dataset-Dependent Effects in Contrastive Forward-Forward Learning
Joshua Steier
Contrastive Forward-Forward (CFF) learning trains Vision Transformers layer by layer against supervised contrastive objectives. CFF training can be sensitive to random seed, but th…
PyHealth 2.0: A Comprehensive Open-Source Toolkit for Accessible and Reproducible Clinical Deep Learning
John Wu, Yongda Fan, Zhenbang Wu +14
Difficulty replicating baselines, high computational costs, and required domain expertise create persistent barriers to clinical AI research. To address these challenges, we introd…