NCA-GENM domain - 25% of the exam

Experimentation

Experimentation is 25% of the NVIDIA-Certified Associate: Generative AI Multimodal (NCA-GENM) exam. These are the objectives it covers, each with practice questions and worked explanations.

Objectives in this domain

Sample question from this domain

Free sampleExperimentationmedium

A diffusion model is conditioned on a text prompt by injecting CLIP text embeddings at multiple layers of the U-Net denoiser. Which mechanism directly uses those embeddings to steer the spatial features of the latent during denoising?

  • ACross-attention layers in the U-Net, where queries come from the spatial feature map and keys and values come from the projected text embeddings Correct
  • BSelf-attention within the U-Net residual blocks, which relates every spatial position to every other spatial position in the same layer
  • CClassifier-free guidance, which blends two separate forward passes through the denoiser at inference time to amplify prompt alignment
  • DAdaptive layer normalisation, which modulates feature statistics using a global pooled representation of the text embedding
Identify the architectural mechanism by which CLIP text embeddings exert spatial control over image generation in diffusion models. In latent diffusion models such as Stable Diffusion, the U-Net denoiser contains cross-attention blocks at multiple resolutions. The spatial feature map provides queries while the CLIP text token embeddings are linearly projected to keys and values. Each spatial position can attend to whichever text tokens are most relevant, creating a direct, token-level conditioning pathway. Self-attention, adaptive normalisation, and classifier-free guidance each play distinct roles but none directly injects the token-level text representation into the spatial feature map the way cross-attention does.

Why A is correct: Cross-attention is the standard conditioning mechanism in latent diffusion models: spatial queries attend to token-level keys and values derived from the text embedding, allowing every spatial region to be guided by the relevant textual context.

Why B is wrong: Self-attention relates spatial positions to each other within the feature map, not to an external conditioning signal such as a text embedding, so it cannot directly inject the CLIP representation.

Why C is wrong: Classifier-free guidance is a sampling-time weighting strategy that scales the difference between conditional and unconditional predictions; it relies on cross-attention conditioning already being present and is not itself the mechanism that injects the embeddings.

Why D is wrong: Adaptive layer normalisation is used in some architectures such as DiT to inject timestep or class conditioning via scale and shift parameters, but it is not the primary mechanism used to inject token-level CLIP text embeddings in the U-Net backbone.

Other domains in this exam

See also the NCA-GENM cert hub, the study guide, and the cheat sheet.

Examworthy is not affiliated with or endorsed by NVIDIA. Original, blueprint-aligned practice material only.