• multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
• embedding — A list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.

A production answer to cold start: represent items by multimodal content embeddings instead of IDs, so member taste transfers to assets with zero interaction history from day one.

• blogIn-House LLM Serving at Netflix
• blogGenRec: Towards LLM-Native Recommendation at Netflix
• blogGenPage: Towards End-to-End Generative Homepage Construction at Netflix

• blogGenRec: Towards LLM-Native Recommendation at NetflixNetflix Technology Blog
• blogGenPage: Towards End-to-End Generative Homepage Construction at NetflixNetflix Technology Blog
• articleNetflix PRS 2024 - Applying LLMs to Recommendation ExperiencesEugene Yan

Checking sign-in…

Loading comments…