Hacker News with Generative AI: Recommendation Systems

Foundation Model for Personalized Recommendation (netflixtechblog.com)
Netflix’s personalized recommender system is a complex system, boasting a variety of specialized machine learned models each catering to distinct needs including “Continue Watching” and “Today’s Top Picks for You.” (Refer to our recent overview for more details). However, as we expanded our set of personalization algorithms to meet increasing business needs, maintenance of the recommender system became quite costly.
BeeFormer: CF and CBF hybrid approach for recommendation systems (github.com/recombee)
This is the official implementation provided with our paper beeFormer: Bridging the Gap Between Semantic and Interaction Similarity in Recommender Systems.
Improving recommendation systems and search in the age of LLMs (eugeneyan.com)
Recommendation systems and search have historically drawn inspiration from language modeling. For example, the adoption of Word2vec to learn item embeddings (for embedding-based retrieval), and using GRUs, Transformer, and BERT to predict the next best item (for ranking). The current paradigm of large language models is no different.
Jagged Flash Attention Optimization (shaped.ai)
Meta researchers have introduced Jagged Flash Attention, a novel technique that significantly enhances the performance and scalability of large-scale recommendation systems.
Show HN: Fashion Shopping with Nearest Neighbors (vibewall.shop)
An error has occurred while loading the content.
Prediction Games (argmin.net)
In 2006, Netflix launched an open competition that would transform machine learning practice. They offered a million dollars to anyone who could improve upon their in-house recommendation system by 10%.
Unifying Generative and Dense Retrieval for Sequential Recommendation (arxiv.org)
Sequential dense retrieval models utilize advanced sequence learning techniques to compute item and user representations, which are then used to rank relevant items for a user through inner product computation between the user and all item representations.
ByteDance's Recommendation System (github.com/bytedance)
Learning Category Trees for ID-Based Recommendation: Differentiable VQ (arxiv.org)
Category information plays a crucial role in enhancing the quality and personalization of recommender systems. Nevertheless, the availability of item category information is not consistently present, particularly in the context of ID-based recommendations.
Show HN: An app where you suggest me your vet, I suggest you my babysitter (play.google.com)
Meta's Trillion Parameter Recommendation System (shaped.ai)
Ask HN: AI for Music Discovery (ycombinator.com)
Show HN: Shepherd 3.0 – Like wandering the aisles of your favorite bookstore (ycombinator.com)