Hamsterdam Research
-
Introducing inference scaling for long-context RAG, and why marketers should care.
Introducing inference scaling for long-context RAG via Google DeepMind, and why marketers should care. Welcome back to 🐹 Hamsterdam Research, where we’re delving into a new topic from Google DeepMind: Inference Scaling for Long-Context RetrievalAugmented Generation. The paper was submitted to ArXiv on October 6th, 2024, and includes several authors, including Zhenrui Yue, Honglei Zhuang,…
-
Introducing Differential Transformer, and why marketers should care.
Introducing Differential Transformer, and why marketers should care. 🐹 Hamsterdam Research is back with a new and exciting topic: Differential Transformer. You may be familiar with Transformers, the basis for ML models like GPT and BERT. A Differential Transformer (Diff Transformer) is an improved version designed to handle attention better by focusing on relevant information…
-
Stumbling Upon Google Engineer Ni Lao’s Work, & Exploring What It Can Teach Us about ML, IR & NLP for SEO Insights (a Hamsterdam Research Post)
In this Hamsterdam Research post, we look at the work of Ni Lao, a Google engineer, for learnings about machine learning, information retrieval, and NLP.