Trending

Meta Details GEM Ads Model Using LLM-Scale Training, Hybrid Parallelism, and Knowledge Transfer

Meta released details about its Generative Ads Model (GEM), a foundation model designed to improve ads recommendation across its platforms. The model addresses core challenges in recommendation systems (RecSys) by processing billions of daily user-ad interactions where meaningful signals such as clicks and conversions are very sparse. By Vinod Goje

[P] Is Spotify Mood analyser+Playlist recommendation worth it

[D] Is Spotify Mood analysis+Playlist recommendation worth it making

[P] Why didn’t semantic item profiles help my GCN recommender model?

Core Of Netflix’s $1 Billion Algorithm - Matrix Factorization.

I spent weeks understanding Netflix's recommendation system - here's what I learned (Matrix Factorization breakdown + working code)

Grok 4 continues to provide absolutely unhinged recommendations

[R] Is the Two-Tower Model Hitting Its Limits for RecSys Retrieval?

[R]Group Recommendation Systems — Looking for Baselines, Any Suggestions?

[D] Future of RecSys in age of LLM