A Biophysical Model for ATAC-seq Data Analysis biorxiv.org/content/10.110…

My paper "Training-free Graph Neural Networks and the Power of Labels as Features" has been accepted to #TMLR 🎉 I proposed training-free (and optionally trained) GNNs. Paper📜：arxiv.org/abs/2404.19288 Code📁：github.com/joisino/laf

Search in Vector Databases.

Linux find command cheatsheet

Final Fantasy 8 World Map - One of my most highly requested maps is finally finished!

Stanford released a 1.5 hours lecture on Building Large Language Models! This lecture provides a concise overview of building a ChatGPT-like model, covering both pretraining (language modeling) and post-training (SFT/RLHF). youtu.be/9vM4p9NN0Ts?si…

Bash Scripting Basics

"Pen and Paper Exercises in #MachineLearning" Free 211-page PDF: arxiv.org/abs/2206.13446 GitHub: github.com/michaelgutmann… ————— #DataScientist #AI #ML #DataScience

Software Development Best Practices Follow Tech with Mak

Neural Network Activation Functions

The Generative AI Tech Stack

LLM = Smart, but works only with what it was trained on. Its knowledge is fixed after training, and when it lacks relevant information, it may generate plausible-sounding but incorrect answers (“hallucinations”). RAG = Smart + can “look things up” in real time. It retrieves

I struggled with git until I learned these 17 commands:

The most important AI paper of 2025 might have just dropped. NVIDIA lays out a framework for Small Language Model agents that could outcompete LLMs. Here’s the full breakdown (and why it matters):

I just found out MIT Press released a free Deep Learning fundamentals book with theory, code, and slides. Learning these fundamentals is key if you want to get serious with AI. The book includes DL math, training techniques, CNNs, graph neural nets, and transformers.

The best visual guide to LLMs you’ll ever see

This 277 page PDF unlocks the secrets of Large Language Models. Here's what's inside: 🧵

LLM Prompting Techniques [ Read. Learn. Bookmark. Follow Tech with Mak ] Let's go! Prompting isn’t just asking the AI a question. It’s a deliberate, engineered input design process, and a critical skill when working with Large Language Models (LLMs). Let's breakdown the

Google just dropped another banger 🤯 It’s called PaperBanana, a new tool that generates publication-ready academic illustrations directly from your methodology text. 100% Free.