What are the modern TTS models (Tortoise, XTTS, StyleTTS2, ElevenLabs)?
Machine Learning / AI
What is vLLM and why is PagedAttention needed?
What is the difference between convolution and cross-correlation?
What is a 1x1 convolution and what is it used for?
Design an OCR + NLP system for processing scanned contracts.
Describe the architecture of U-Net and why skip connections are used there.
How to ensure data security in RAG (PII, access rights)?
How do you combine RAG with tool use and function calling?
Which tasks do GANs still solve better than diffusion models (real-time, low-latency)?
What is self-supervised learning and why has it become the foundation of foundation models?
What are adapter tuning and prefix tuning?
What is anchor matching and what criteria are used?
What is grounding DINO and open-vocabulary detection?
How to do post-processing of masks (CRF, morphological operations)?