OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration Paper • 2602.05400 • Published 15 days ago • 319
Linear representations in language models can change dramatically over a conversation Paper • 2601.20834 • Published 22 days ago • 21
Less is More: Recursive Reasoning with Tiny Networks Paper • 2510.04871 • Published Oct 6, 2025 • 508