Showing 2026Show all
2 papers · 1 filter
cs.AI2026
Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding
Hoang Phan, Minh Pham, Chau Pham +3
On-policy reinforcement learning has become a central paradigm for improving the reasoning abilities of large language models. However, its effectiveness is often limited by reward…
cs.LG2026
Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales
Shikai Qiu, Zixi Chen, Hoang Phan +2
Several recently introduced deep learning optimizers utilizing matrix-level preconditioning have shown promising speedups relative to the current dominant optimizer AdamW, particul…