Showing 2026Show all
3 papers · 1 filter
cs.LG2026
When Losses Align: Gradient-Based Composite Loss Weighting for Efficient Pretraining
Ivan Karpukhin, Andrey Savchenko
Modern deep models are often pretrained on large-scale data with missing labels using composite objectives, where the relative weights of multiple loss terms act as hyperparameters…
cs.LG2026
Embedding-Aware Feature Discovery: Bridging Latent Representations and Interpretable Features in Event Sequences
Artem Sakhno, Ivan Sergeev, Alexey Shestov +5
Industrial financial systems operate on temporal event sequences such as transactions, user actions, and system logs. While recent research emphasizes representation learning and l…
cs.IR2026
Financial Transaction Retrieval and Contextual Evidence for Knowledge-Grounded Reasoning
Artem Sakhno, Daniil Tomilov, Yuliana Shakhvalieva +5
Nowadays, success of financial organizations heavily depends on their ability to process digital traces generated by their clients, e.g., transaction histories, gathered from vario…