What are diffusion audio models (AudioLDM)?
Machine Learning / AI
What are guardrail metrics?
What is a model card and why is it needed?
What is a VAE-encoder in Stable Diffusion and what is it used for?
What is early stopping in boosting and how to validate it correctly?
What are the uplift use cases in marketing (target population)?
What are reference-free and reference-based metrics?
What types of data quality issues have you encountered?
What tasks do KG embeddings solve (link prediction, entity typing)?
What is a membership inference attack?
What is domain randomization?
Explain the idea of word2vec. How does CBOW differ from Skip-gram?
What are scaling laws (Kaplan, Chinchilla)? How do they relate model size, data, and compute?
What is visual servoing?
What is intermittent demand forecasting (Croston)?
What are the models of text detection in images (DBNet, EAST, CRAFT)?
How is LoRA trained for Stable Diffusion?
What are EFB and GOSS in LightGBM?
Which LoRA hyperparameters are important (r, alpha, target_modules)?
What are time-varying covariates?