Why a decades old architecture decision is impeding the power of AI computing
Explainer
Peter Hess
Blog
Categories
Popular topics
304 results for AI
For LLMs, IBM’s NorthPole chip overcomes the tradeoff between speed and efficiency
ResearchPeter HessHow memory augmentation can improve large language model efficiency and flexibility
ResearchPeter HessIntroducing Prithvi WxC, a new general-purpose AI model for weather and climate
NewsKim MartineauReinventing data preparation on cloud to scale enterprise AI
NewsMike MurphyTraining AI models faster than ever
NewsPeter HessHudson Forum 2024: Building the future with collaboration and math
NewsMike MurphySimplify your Code LLM solutions using CodeLLM DevKit
Technical noteRangeet Pan, Rahul Krishna, Saurabh Sinha, Raju Pavuluri, and Maja VukovicA toxic language filter built for speed
NewsKim MartineauHow IBM Research built a lab for the future of computing
Deep DiveMike MurphyImproving Hugging Face training efficiency through packing with flash attention
Technical noteRhui Dih Lee, Arthur Zucker, Achintya Kundu, Laura Wynter, Raghu Ganti, and Mayank MishraBreaking down the AI transformer
ExplainerKim MartineauIntroducing KVP10k: A comprehensive dataset for key-value pair extraction in business documents
Technical noteTal Drory, Udi Barzelay, and Oshri NaparstekTeaching AI models to improve themselves
ResearchPeter HessDetecting health and science misinformation with AI
ResearchPeter HessIBM Granite led open-source LLMs on API calling
NewsKim MartineauIBM and RPI researchers demystify in-context learning in large language models
NewsPeter Hess
