4 papers
Sona Technical Report
Sona Team, Alexandr Udeneev, Aleksei Krasilnikov +33
We introduce Sona, a single-model generative recommender for Yandex Music. In an online A/B test, Sona replaced the entire production cascade, comprising more than 15 candidate gen…
Session-Level Optimization for Large-Scale Retrieval using REINFORCE with Multi-Step Off-Policy Correction
Artem Matveev, Sergei Makeev, Aleksei Krasilnikov +3
Two-tower models are a widely used paradigm for large-scale retrieval in recommendation. However, they are typically trained with myopic supervised objectives, such as next-item pr…
Gated Bidirectional Linear Attention for Generative Retrieval
Artem Matveev, Vladislav Tytskiy, Sergei Makeev +1
In recommender systems, generative retrieval typically uses an encoder-decoder setup: an encoder processes a user interaction history, and an autoregressive decoder then generates…
Correcting the LogQ Correction: Revisiting Sampled Softmax for Large-Scale Retrieval
Kirill Khrylchenko, Vladimir Baikalov, Sergei Makeev +2
Two-tower neural networks are a popular architecture for the retrieval stage in recommender systems. These models are typically trained with a softmax loss over the item catalog. H…