On Data Engineering for Scaling LLM Terminal Capabilities Paper • 2602.21193 • Published 5 days ago • 89
PaperBanana: Automating Academic Illustration for AI Scientists Paper • 2601.23265 • Published 30 days ago • 204
Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs Paper • 2602.10388 • Published 19 days ago • 236
Green-VLA: Staged Vision-Language-Action Model for Generalist Robots Paper • 2602.00919 • Published 29 days ago • 305
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration Paper • 2602.05400 • Published 24 days ago • 341
Linear representations in language models can change dramatically over a conversation Paper • 2601.20834 • Published Jan 28 • 21
Less is More: Recursive Reasoning with Tiny Networks Paper • 2510.04871 • Published Oct 6, 2025 • 509