What are GIoU, DIoU, CIoU loss?
Machine Learning / AI
What are the quality assessment metrics for audio generation (FAD, MOS)?
What is SLAM and how is ML integrated with classical methods?
What is FPN and why is it needed?
How to handle tool call errors in the agent (retry, fallback)?
What is a video transformer (ViViT, TimeSformer)?
What are DVC and Git LFS for data versioning?
What are the metrics for evaluating uplift models (Qini, uplift curve)?
What is a cross-encoder and how does it differ from a bi-encoder?
What features of video processing differ from image processing?
How does TF-IDF differ from frequency representation and why is it needed?
What is multi-query attention and where is it used?
What is the Unigram language model in tokenization (like in SentencePiece)?
Tell us about a machine translation task. What is sequence-to-sequence?
What is RVQ (residual vector quantization) in an audio codec?
What is inverse RL?
What are foundation models in medicine (MedSAM, RadGraph)?
What is ROUGE and how does ROUGE-L differ from ROUGE-N?
What is Inverse Propensity Scoring in LTR?
What data deduplication techniques are used in a pipeline?