activity
20242026
collaborators

6 papers

cs.LG2026

A Foundation Model for Multimodal Event Sequences in Financial Applications

Nikita Rusakov, Vladislav Meshkov, Konstantin Zorin +4

Predictive modeling is a core component of modern financial services, where a wide range of tasks are traditionally addressed using separate models trained on manually engineered t…

cs.IR2026

Pre-trained LLMs Meet Sequential Recommenders: Efficient User-Centric Knowledge Distillation

Nikita Severin, Danil Kartushov, Vladislav Urzhumov +8

Sequential recommender systems have achieved significant success in modeling temporal user behavior but remain limited in capturing rich user semantics beyond interaction patterns.…

cs.IR2026

Sparse Autoencoders for Sequential Recommendation Models: Interpretation and Flexible Control

Anton Klenitskiy, Konstantin Polev, Daria Denisova +3

Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important…

cs.IR2025

Let It Go? Not Quite: Addressing Item Cold Start in Sequential Recommendations with Content-Based Initialization

Anton Pembek, Artem Fatkulin, Anton Klenitskiy +1

Many sequential recommender systems suffer from the cold start problem, where items with few or no interactions cannot be effectively used by the model due to the absence of a trai…

cs.IR2025

Time to Split: Exploring Data Splitting Strategies for Offline Evaluation of Sequential Recommenders

Danil Gusak, Anna Volodkevich, Anton Klenitskiy +2

Modern sequential recommender systems, ranging from lightweight transformer-based variants to large language models, have become increasingly prominent in academia and industry due…

cs.IR2024

RePlay: a Recommendation Framework for Experimentation and Production Use

Alexey Vasilev, Anna Volodkevich, Denis Kulandin +2

Using a single tool to build and compare recommender systems significantly reduces the time to market for new models. In addition, the comparison results when using such tools look…