Archive 124 issues
#99 Architecture PRO edition
Graph Neural Networks (GNNs), Simply Explained
#98 RL PRO edition
World Models, Simply Explained
#97 RL PRO edition
Reinforcement Learning for Large Language Models, Simply Explained
#96 LLMs PRO edition
MicroGPT, Simply Explained
#95 Multimodal PRO edition
Multimodal Large Language Models (MLLMs), Simply Explained
#94 Theory PRO edition
Conformal Prediction: Reliable Uncertainty for Machine Learning
#93 Multimodal PRO edition
Vision Language Models (VL-JEPA), Simply Explained
#92 Theory PRO edition
The Lottery Ticket Hypothesis, Simply Explained
#91 Architecture PRO edition
Linear Attention For Transformers (Kimi Linear), Simply Explained
#90 Papers PRO edition
NeurIPS 2025 Paper Awards (The Best Papers of 2025)
#89 Papers PRO edition
The Best NeurIPS Papers of 2025, Simply Explained
#88 LLMs PRO edition
NRGPT: Combining Energy-Based Models With GPT
#87 Training PRO edition
Fine-Tuning for LLMs, Simply Explained
#86 Inference PRO edition
A Deep Dive into Modern Transformers: RoPE, Activation Functions, Quantization
#85 Inference PRO edition
A Deep Dive into Modern Transformers: Optimizing Attention
#84 Interp. PRO edition
Machine Learning Explainability (XAI), Simply Explained
#83 Inference PRO edition
GPU Optimization for Machine Learning, Simply Explained
#82 Training PRO edition
Neural Network Backpropagation, Mathematically Explained
#81 Theory PRO edition
Dimensionality Reduction: t-SNE and UMAP
#80 Foundation PRO edition
Boosting Models in Machine Learning, Simply Explained
#79 Safety PRO edition
LLM Security (Prompt Injection, Adversarial Attacks), Simply Explained
#78 Training PRO edition
LLM Knowledge Distillation, Simply Explained
#77 Architecture PRO edition
Energy-Based Transformers (EBTs), Simply Explained
#76 Architecture PRO edition
Neural Radiance Fields (NeRFs), Simply Explained