Sequential recommender systems are typically trained with next-item cross-entropy (CE), yet evaluated by top-N ranking metrics that reward relative item ordering in the recommendation slate. This mismatch remains unaddressed for strong collaborative sequential models. Recent group-relative reinforcement learning has sh...
Danil Gusak, Evgeny Frolov· Proceedings of the 35th ACM...· 1 citation
Recommender systems are increasingly expected to combine interaction histories with language. In many cases, a user's next choice may depend on a temporary situation---such as their current mood, plans, or constraints---that is not visible in past behavior. Existing benchmarks, however, mostly evaluate average next-ite...
Nikita Sukhorukov, Danil Gusak, A. Petrova et al.· Proceedings of the 35th ACM...· 1 citation
Semantic IDs (SIDs) are becoming a practical interface for generative recommendation. Existing pipelines usually build them by quantizing frozen content embeddings, implicitly assuming that content similarity is the right geometry for recommendation. This assumption is often too strong: items that look similar in conte...
Valentin Tsaruk, Danil Gusak, Rostislav Korst et al.· Proceedings of the 35th ACM...· 0 citations
Recommender systems are increasingly expected to combine interaction histories with language. In many cases, a user's next choice may depend on a temporary situation---such as their current mood, plans, or constraints---that is not visible in past behavior. Existing benchmarks, however, mostly evaluate average next-ite...
Nikita Sukhorukov, Danil Gusak, A. Petrova et al.· 1 citation
Sequential recommender systems are typically trained with next-item cross-entropy (CE), yet evaluated by top-N ranking metrics that reward relative item ordering in the recommendation slate. This mismatch remains unaddressed for strong collaborative sequential models. Recent group-relative reinforcement learning has sh...
Danil Gusak, Evgeny Frolov· Proceedings of the 35th ACM...· 1 citation
This thesis is that SID utility is regime-dependent: model capacity, catalog scale, and interaction density jointly determine whether semantic structure helps or is redundant, and argues that SID utility is regime-dependent.
Danil Gusak, Evgeny Frolov· Proceedings of the 20th ACM...· 6 citations
Generative recommenders retrieve items by autoregressively decoding semantic IDs (SIDs). The standard autoregressive SID interface (SID-AR) represents each history item with K code tokens, expanding a T-item history to TK tokens, while trie-constrained beam search repeatedly re-enters the full backbone during generatio...
Danil Gusak, A. Volodkevich, Evgeny Frolov· Proceedings of the 20th ACM...· 3 citations
Codebook-based semantic IDs (SIDs), short discrete code sequences produced by quantization over item representations, made generative recommendation practical by turning catalog-scale retrieval into low-cardinality generation. Yet the same interface now concentrates the field’s hardest questions. We revisit the canonic...
Danil Gusak, Evgeny Frolov· Proceedings of the 20th ACM...· 3 citations
CoSID is introduced, a concept-conditioned SID decoder that encodes the history once into a compact next-item concept and delegates the entire beam search to a lightweight KV-cached decoder.
Danil Gusak, A. Volodkevich, Evgeny Frolov· Proceedings of the 20th ACM...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.