PinnedDr. Ashish Bamania‘AI In 100 Images’: I’m Making My New Book Available For FreeHere’s a Collection of 100 Stunning Visuals with Clear, Concise & No-fluff Explanations of 100 Must-Know Concepts in AI todayJun 72Jun 72
PinnedDr. Ashish BamaniaMy Most Viewed Medium Stories (Updated Weekly)My Story Stats On MediumAug 6, 20233Aug 6, 20233
Dr. Ashish BamaniainLevel Up CodingAn LLM With A Visual Sketchpad Can Now Smash Its Competitors Without One (Even GPT-4o)A deep dive into the “Sketchpad” framework that enables LLMs to draw and reason via the “Visual Chain-of-Thought Prompting” approachJul 203Jul 203
Dr. Ashish BamaniainLevel Up CodingHere Is Google DeepMind’s New Research To Build Massive LLMs With A Mixture Of Million ExpertsA deep dive into the the Mixture-of-a-Million-Experts (MoME) architecture, which outperforms traditional LLMs like never beforeJul 137Jul 137
Dr. Ashish BamaniainLevel Up CodingThe New ‘Adam-mini’ Optimizer Is Here To Cause A Breakthrough In AIA deep dive into how Optimizers work, their developmental history, and how the 'Adam-mini' optimizer enhances LLM training like never…Jul 55Jul 55
Dr. Ashish BamaniainLevel Up CodingA Squad Of Open-Source LLMs Can Now Beat OpenAI’s Closed-Source GPT-4oA deep dive into how the Mixture-of-Agents (MoA) model leverages the collective strengths of multiple open-source LLMs and beats GPT-4oJun 3010Jun 3010
Dr. Ashish BamaniainLevel Up CodingKolmogorov-Arnold Networks (KANs) Are Being Used To Boost Graph Deep Learning Like Never BeforeA deep dive into how Graph Kolmogorov-Arnold Networks (GKANs) are improving Graph Deep Learning to surpass traditional approachesJun 263Jun 263
Dr. Ashish BamaniainLevel Up CodingSuperfast Matrix-Multiplication-Free LLMs Are Finally HereA deep dive into Matrix-Multiplication-Free LLMs that might drastically decrease the use of GPUs in AI, unlike todayJun 208Jun 208
Dr. Ashish BamaniainLevel Up CodingGoogle’s New Algorithms Just Made Searching Vector Databases Faster Than EverA Deep Dive into how Google’s ScaNN and SOAR Search algorithms supercharge the performance of Vector DatabasesJun 185Jun 185