ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training Paper • 2609.00188 • Published 3 days ago • 38
SmolLM3 pretraining datasets Collection datasets used in SmolLM3 pretraining • 15 items • Updated Aug 12, 2025 • 56
view article Article Cosmopedia: how to create large-scale synthetic data for pre-training Large Language Models +1 loubnabnl, anton-l, davanstrien • Mar 20, 2024 • 115