Prompt category
ML Architecture
Transformer, agent, RAG, diffusion, GAN, GNN, U-Net, and MoE diagrams.
Decoder-Only LLM Architecture (GPT-Style)
Stacked decoder blocks with masked self-attention and a language modeling head.
Diffusion Model Forward & Reverse Process
Forward noising chain and reverse denoising chain with a U-Net at each step.
GAN Training Loop
Generator vs Discriminator adversarial loop with labeled losses and gradient flow.
Graph Neural Network Message Passing
Node feature update via neighborhood aggregation across L message-passing layers.
Mixture-of-Experts (MoE) Layer
Sparse routing of tokens through a gating network into top-k experts.
Multi-Agent Collaboration Framework
Closed-loop diagram with Planner, Retriever, Executor and Critic agents and an external knowledge base.
Retrieval-Augmented Generation (RAG) Pipeline
Query embedding, vector retrieval, prompt augmentation and LLM response generation.
Transformer Encoder-Decoder Architecture
Publication-quality transformer block diagram with self-attention, cross-attention, and residual connections.
U-Net Encoder-Decoder for Segmentation
Symmetric encoder-decoder with skip connections for pixel-wise prediction.
Vision Transformer (ViT) Architecture
Patch embedding, position encoding, transformer encoder stack and a classification head.