deep-learning 11
- MicroGPT Architecture: Pure Python Autograd and Transformer Foundations
- NVIDIA CUDA Tile Architecture: High-Level Tile-Based GPU Programming
- Mixture-of-Experts Architecture: From Sparse Routing to Fine-Grained LLaMA 4 Scaling
- Building an End-to-End LLM from Scratch: Analyzing Karpathy's LLM101n Curriculum
- From Sequential RNNs to Transformers: Mathematics of Self-Attention and Scaled Encoders
- From Word Embeddings to Attention: The Foundations of Transformer NLP Architectures
- ViViD: Video Virtual Try-On Using Diffusion Models and Temporal Attention
- Foundational AI Architectures: Mapping the Canonical Papers of Modern Deep Learning
- Dual-Engine Mechanics of Transformers: Attention and Feedforward Layers
- Self-Attention by Hand: Mathematical Mechanics of Scaled Dot-Product Attention
- Solving Non-Linear Separability: From XOR Perceptrons to Deep Autograd Networks