Rio Yokota

4

Papers

9

Total Citations

Papers (4)

Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization

Variational Learning Finds Flatter Solutions at the Edge of Stability

NeurIPS 2025arXiv

Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation

Variational Learning is Effective for Large Deep Networks