Transformer, multi-agent, RAG, GAN and other neural network architecture diagrams for top-venue papers.
10 prompts
Closed-loop diagram with Planner, Retriever, Executor and Critic agents and an external knowledge base.
Publication-quality transformer block diagram with self-attention, cross-attention, and residual connections.
Stacked decoder blocks with masked self-attention and a language modeling head.
Forward noising chain and reverse denoising chain with a U-Net at each step.
Generator vs Discriminator adversarial loop with labeled losses and gradient flow.
Node feature update via neighborhood aggregation across L message-passing layers.
Sparse routing of tokens through a gating network into top-k experts.
Query embedding, vector retrieval, prompt augmentation and LLM response generation.
Symmetric encoder-decoder with skip connections for pixel-wise prediction.
Patch embedding, position encoding, transformer encoder stack and a classification head.