More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models Paper • 2509.25848 • Published 25 days ago • 77
Instella ✨ Collection Announcing Instella, a series of 3 billion parameter language models developed by AMD, trained from scratch on 128 Instinct MI300X GPUs. • 12 items • Updated Aug 10 • 8
SAND-Math: Using LLMs to Generate Novel, Difficult and Useful Mathematics Questions and Answers Paper • 2507.20527 • Published Jul 28 • 5
SAND-Math: Using LLMs to Generate Novel, Difficult and Useful Mathematics Questions and Answers Paper • 2507.20527 • Published Jul 28 • 5 • 2