Steerable Multi-Objective Group-Relative Preference Optimization with Jointly Trained Low-Rank Adapters Paper • 2611.09634 • Published 8 days ago • 11
Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibility Paper • 2608.03930 • Published Aug 4 • 10
Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibility Paper • 2608.03930 • Published Aug 4 • 10