6 papers
AdaMem: Adaptive Memory Token Allocation for Soft Compression in Retrieval-Augmented Generation
Artem Sakhno, Grigorii Davydenko, Omar Zoloev +3
Retrieval-augmented generation (RAG) improves language models with retrieved evidence, but processing many long passages is costly and can introduce distracting information. Soft c…
Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation
Julia Belikova, Rauf Parchiev, Evgeny Egorov +4
Procedural memory is increasingly used to improve LLM agents on recurring workplace tasks, yet its ability to produce reusable skills remains poorly understood. We introduce AFTER,…
Topological Metric for Unsupervised Embedding Quality Evaluation
Aleksei Shestov, Anton Klenitskiy, Daria Denisova +4
Modern representation learning increasingly relies on unsupervised and self-supervised methods trained on large-scale unlabeled data. While these approaches achieve impressive gene…
Automated Evolutionary Optimization for Resource-Efficient Neural Network Training
Ilia Revin, Leon Strelkov, Vadim A. Potemkin +2
There are many critical challenges in optimizing neural network models, including distributed computing, compression techniques, and efficient training, regardless of their applica…
LATTE: Learning Aligned Transactions and Textual Embeddings for Bank Clients
Egor Fadeev, Dzhambulat Mollaev, Aleksei Shestov +6
Learning clients embeddings from sequences of their historic communications is central to financial applications. While large language models (LLMs) offer general world knowledge,…
LLM4ES: Learning User Embeddings from Event Sequences via Large Language Models
Aleksei Shestov, Omar Zoloev, Maksim Makarenko +4
This paper presents LLM4ES, a novel framework that exploits large pre-trained language models (LLMs) to derive user embeddings from event sequences. Event sequences are transformed…