Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
portfolio
publications
Correcting the LogQ Correction: Revisiting Sampled Softmax for Large-Scale Retrieval Permalink
Published in RecSys 2025
Kirill Khrylchenko, Vladimir Baikalov, Sergei Makeev, Artem Matveev, Sergei Liamaev
A refined logQ correction for in-batch sampled softmax that removes the residual bias from the always-present positive item, giving consistent gains for large-scale two-tower retrieval on public and proprietary datasets.
Scaling Recommender Transformers to One Billion Parameters Permalink
Published in KDD 2026, Jeju Island, Republic of Korea
Kirill Khrylchenko, Artem Matveev, Sergei Makeev, Vladimir Baikalov
A recipe for scaling generative-recommender transformers to one billion parameters by decomposing autoregressive user-history modeling into feedback and next-item prediction; deployed on a large-scale music platform for +2.26% listening time and +6.37% likes in online A/B tests.
Gated Bidirectional Linear Attention for Generative Retrieval Permalink
Published in SIGIR 2026
Artem Matveev, Vladislav Tytskiy, Sergei Makeev, Sergei Liamaev
A linear-time bidirectional attention layer (GBLA) for generative retrieval that matches full self-attention quality while reaching up to 8.2× single-layer speedup on very long user histories.
Long-Term Optimization for Large-Scale Generative Retrieval with Off-Policy REINFORCE Permalink
Published in KDD 2026, 5th Workshop on End-to-End Customer Journey Optimization
Artem Matveev, Sergei Makeev, Aleksei Krasilnikov, Vladimir Baikalov, Sergei Liamaev, Kirill Khrylchenko
Training generative retrievers with off-policy REINFORCE to optimize long-term user satisfaction instead of next-item accuracy, with doubly robust evaluation and test-time scaling that improves cumulative session reward on Yambda-5B.
Embedding Items at Scale: Comparing GNN-Based and ID-Based Item Embeddings in the Yandex Ecosystem Permalink
Published in arXiv preprint
Sergei Makeev, Artem Matveev, Vladimir Baikalov, Kirill Khrylchenko
An industrial case study comparing pretrained GNN item embeddings with end-to-end trainable ID embeddings for transformer-based sequential recommenders across Yandex Market, Yandex Music, and a public low-resource Yandex Lavka dataset.
Sona Technical Report Permalink
Published in arXiv preprint
Sona Team: Alexandr Udeneev, Aleksei Krasilnikov, Alexey Nadtochiy, Andrey Semenov, Andrey Tsyrkunov, Anna Krivonos, Anna Lipkina, Artem Matveev, et al. (34 authors)
A single generative recommender that replaced the entire production cascade at Yandex Music — 15+ candidate generators plus pre-ranking and ranking models — while lifting Active Users by 4.53%, Total Listening Time by 6.30%, and Likes by 11.42% in an online A/B test.
talks
Do We Need Graph Neural Networks to Encode Items in Recommendations? Permalink
Published:
Talk at Yandex For ML on graph neural networks for item representation in recommender systems.