GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models Paper • 2410.05229 • Published Oct 7 • 18
OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework Paper • 2404.14619 • Published Apr 22 • 126
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data Paper • 2404.15653 • Published Apr 24 • 26