Towards Scalable Pre-training of Visual Tokenizers for Generation Paper • 2512.13687 • Published 10 days ago • 93
MedGemma Release Collection Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications. • 7 items • Updated Jul 11 • 366
Cell2Sentence Models Collection Cell2Sentence models trained for single-cell tasks • 5 items • Updated Apr 16 • 14
Sparse Autoencoders Find Highly Interpretable Features in Language Models Paper • 2309.08600 • Published Sep 15, 2023 • 15