What features are used in classic NLP models (TF-IDF, n-grams, character n-grams)?
Machine Learning / AI
What is Named Entity Recognition (NER)? What annotation is most commonly used (BIO, BIOES)?
What is the role of residual connection and LayerNorm in a Transformer block?
What are the problems of face/hand artifacts in diffusion models and how to combat them?
What is a bounding box and what are the coordinate formats (xyxy, xywh, cxcywh)?
What is IVF index and why are centroids needed?
What is atrous (dilated) convolution and how does it expand the receptive field?
What is diarization and what approaches are there (clustering, EEND)?
What is stochastic depth and why is it used in EfficientNet?
What is the difference between coco mAP and Pascal VOC mAP?
Compare classification, localization, and detection.
How does the BERT model differ from GPT in architecture and training task?
What is chain-of-verification (CoVe)?