IMU-1: Sample-Efficient Pre-training of Small Language Models Paper • 2602.02522 • Published Jan 25 • 9
Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning Paper • 2605.14386 • Published May 14 • 67
Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better Paper • 2602.05393 • Published Feb 5 • 9
Nanbeige4-3B Technical Report: Exploring the Frontier of Small Language Models Paper • 2512.06266 • Published Dec 6, 2025 • 8