Guest post: Enhancing RAG with RA-DIT: A Fine-Tuning Approach to Minimize LLM Hallucinations*

RA-DIT, or Retrieval-Augmented Dual Instruction Tuning, is a method for fine-tuning both the LLM and the retriever in a RAG setup to enhance overall response quality

🌁#83: GAN is back

we’re revisiting classics. Are GANs still worthy of their title as one of the most captivating ideas in ML? plus collection of interesting articles, relevant news and must-read research papers. Dive in!

🦸🏻#7: From Agentic AI to Physical AI

How Jensen Huang worked backwards to start creating the future for the world + trends in AI and Robotics to keep an eye on

What is HtmlRAG, Multimodal RAG and Agentic RAG?

We explore in details three RAG methods that address limitations of original RAG and meet the upcoming trends of the new year

🌁#82: AI and ML in Real Life

Reporting from CES, featuring Jensen Huang's keynote and announcements

Guest Post: AI in 2025: A Combinatorial Explosion of Possibilities, but NOT AGI

opinion paper

🦄 Every Gen AI and AI Infra Unicorn We Covered in 2024

A Year of Innovation: Revisiting the Trailblazing Companies Shaping the Future of AI

🎄 Recap: 21 Episodes of AI 101 Guide

Take some time to learn or refresh the key concepts, techniques, and models that matter most

🌁#81: Key AI Concepts to Follow in 2025

RL, FL, Inference, time-test compute etc will certainly be in your vocab the next year, plus an announcement: TP on HF

15 Agentic Systems and Frameworks of 2024

The best books about AI&ML, 2024 edition

For Your Holiday Reading

Topic 21: What is Natural Language Reinforcement Learning (NLRL)?

Explore how RL can be blended with natural language