?
3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark
Ch. 1353. P. 26625–26665.
Though Large Vision-Language Models (LVLMs) are being actively explored in medicine, their ability to conduct complex real-world telemedicine consultations combining accurate diagnosis with professional dialogue remains underexplored. This paper presents 3MDBench (Medical Multimodal Multi-agent Dialogue Benchmark), an open-source framework for simulating and evaluating LVLM-driven telemedical consultations. 3MDBench simulates patient variability through temperament-based Patient Agent and evaluates diagnostic accuracy and dialogue quality via Assessor Agent. It includes 2996 cases across 34 diagnoses from real-world telemedicine interactions, combining textual and image-based data. The experimental study compares diagnostic strategies for widely used open and closed-source LVLMs. We demonstrate that multimodal dialogue with internal reasoning improves F1 score by 6.5% over non-dialogue settings, highlighting the importance of context-aware, information-seeking questioning. Moreover, injecting predictions from a diagnostic convolutional neural network into the LVLM’s context boosts F1 by up to 20%. Source code is available at https://github.com/univanxx/3mdbench.
In book
Association for Computational Linguistics, 2025.
Silakov D., Системный администратор 2026 С. 84–89
Social media users rarely think about what lies behind the beautiful facade of activity feeds, teeming with photos and video stories. However, the widespread popularity of such platforms generates a huge amount of all sorts of content that needs to be stored, processed quickly, and displayed, and in the era of AI, it also needs ...
Added: September 28, 2026
Ravedovskaya U., Didenko A., Филатова А. А., Journal of Teaching English for Specific and Academic Purposes 2025 Vol. 13 No. 3 P. 529–538
Emergence of generative artificial intelligence (GenAI) is revolutionizing teaching and evaluation in higher education. Early adopters have already demonstrated how large language model (LLM) conversational agents can serve as on-demand tutors, yet empirical evidence regarding their effectiveness in facilitating conceptual learning in non-computational domains is scant. Based on constructivist learning theory, this paper presents a ...
Added: September 18, 2026
Buzaev F., Mullakhmetov R., Bogachev R. et al., Association for Computational Linguistics, 2026.
Playlist generation based on textual queries using large language models (LLMs) is becoming an important interaction paradigm for music streaming platforms. User queries span a wide spectrum from highly personalized intent to essentially catalog-style requests. Existing systems typically rely on non-personalized retrieval/ranking or apply a fixed level of preference conditioning to every query, which can ...
Added: June 22, 2026
Cherednichenko O., Herbert A., Poptsova M., Computational and Structural Biotechnology Journal 2025 Vol. 27 P. 992–1000
Large language models (LLMs) in genomics have successfully predicted various functional genomic elements. While their performance is typically evaluated using genomic benchmark datasets, it remains unclear which LLM is best suited for specific downstream tasks, particularly for generating whole-genome annotations. Current LLMs in genomics fall into three main categories: transformer-based models, long convolution-based models, and state-space models ...
Added: June 19, 2026
Severin N., Kartushov D., Urzhumov V. et al., , in: Advances in Information Retrieval: 48th European Conference on Information Retrieval, ECIR 2026, Delft, The Netherlands, March 29 – April 2, 2026, Proceedings, Part II. (LNCS, volume 16484).: Cham: Springer Publishing Company, 2026. P. 508–517.
Sequential recommender systems have achieved significant success in modeling temporal user behavior but remain limited in cap-turing rich user semantics beyond interaction patterns. Large Language Models (LLMs) present opportunities to enhance user understanding with their reasoning capabilities, yet existing integration approaches cre-ate prohibitive inference costs in real time. To address these limitations, we present a ...
Added: June 18, 2026
Abdullaeva I., Karpukhin I., Filatov A. et al., IEEE Access 2026 Vol. 14 P. 59390–59408
Event sequences, a specialized type of tabular data annotated with timestamps, are prevalent across practical domains such as finance, retail, social networks, and healthcare. Despite the importance of event sequence modeling and analysis, there has been little effort to adapt Large Language Models (LLMs) to this domain. In this paper, we propose a novel solution ...
Added: June 16, 2026
Soloshenko K., Shatalina A., Marina S. et al., , in: Proceedings of the 9th Student Research Workshop associated with the International Conference Recent Advances in Natural Language Processing.: Shumen: INCOMA Ltd, 2025. P. 62–69.
In our research paper we present the approach that is aimed at effectively expanding the context through integrating a database of associative memory into the pipeline. In order to improve long-term memory and personalization we have utilized methods close to Retrieval-Augmented Generation (RAG). Our method uses a multi-agent pipeline with a cold-start agent for initial ...
Added: May 12, 2026
JOURNAL OF EDUCATIONAL TECHNOLOGY DEVELOPMENT AND EXCHANGE 2026 Vol. 19 No. 2 P. 141–169
Educational assessments, from low-stakes classroom tests to high-stakes national examinations, require item pools that are valid, fair, and secure. Automated Item Generation (AIG) aims to efficiently produce large pools of calibrated test items. This paper adopts a two-part design: (1) a brief historical mapping situating LLM-based AIG within the broader AIG trajectory; and (2) a ...
Added: May 5, 2026
Vladimir Bogachev, Aletov V., Alexander Molozhavenko et al., , in: The Fourteenth International Conference on Learning Representations (ICLR 2026).: ICLR, 2026. Ch. 20503 P. 1–26.
This work presents a novel, fully Riemannian framework for Low-Rank Adaptation (LoRA) that geometrically treats low-rank adapters by optimizing them directly on the fixed-rank manifold. This formulation eliminates the parametrization ambiguity present in standard Euclidean optimizers. Our framework integrates three key components to achieve this: (1) we derive Riemannion, a new Riemannian optimizer on the fixed-rank ...
Added: April 29, 2026
Сулейкин А. С., Сорокина В., Пятецкий В. Е., , in: 2025 7th International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency.: [б.и.], 2025. P. 748–753.
Effective metadata management is fundamental to data governance, ensuring that data assets are discoverable, understandable, and usable across the enterprise. However, traditional metadata systems often remain purely technical, describing structures without conveying business meaning. This disconnect — known as the semantic gap — limits the interpretability and value of metadata for business users. To address ...
Added: April 17, 2026
СПб.: Санкт-Петербургский Федеральный исследовательский центр РАН, 2025.
Двадцать вторая Национальная конференция по искусственному интеллекту с международным участием КИИ-2025 продолжает традицию советских (российских) конференций, организуемых Российской ассоциацией искусственного интеллекта. В первом томе трудов публикуются пленарные доклады и доклады участников конференции, представленные на следующих секциях: Секция 1 «Инженерия знаний», Секция 2 «Интеллектуальный анализ данных», Секция 3 «Моделирование рассуждений», Секция 4 «Интеллектуальный анализ текстов, большие ...
Added: February 15, 2026
Vasilevsky V., Alexandrov D., Proceedings of the Institute for System Programming of the RAS 2025 Vol. 37 No. 5 P. 173–182
Automatic code generation by large language models (LLMs) has achieved significant success, yet
it still faces challenges when dealing with complex and large codebases, especially in languages like Java. The
limitations of LLM context windows and the complexity of debugging generated code are key obstacles. This
paper presents an approach aimed at improving Java code generation and debugging. ...
Added: December 26, 2025
Karavaeva E., Vasilevsky V., Ланин Г. М. et al., Труды Института системного программирования РАН 2025 Т. 37 № 4 С. 175–190
The ongoing digitalization of education requires new ways of presenting information and attention retention mechanisms. The aim of the presented work is to propose a solution for implementing a large language model, which will interactively generate prompts of different types, within an e-learning course on programming. The main approaches are the analysis of existing relatively ...
Added: December 25, 2025
David Arteaga, Poptsova M., Computational and Structural Biotechnology Journal 2026 Vol. 31 P. 82–93
Accurate predictions and large-scale identification of protein-protein interactions (PPIs) are crucial for understanding their inherent biological mechanisms and protein functions in virtually all biological processes. Nowadays, graph-based deep learning models have made significant contributions in modeling proteins with physicochemical and geometric features. However, most of these models rely on conventional graph construction methods, such as ...
Added: December 22, 2025
Абрамова А. В., Белоусова Е. Н., Ватюков С. Е. et al., Проблемы стандартизации в здравоохранении 2025 № 5-6 С. 3–14
The improvement of artificial intelligence (AI) technologies and their rapid integration into the socially and economically significant medical industry create broad prospects for ensuring accessibility and quality of medical care, while at the same time creating new challenges related to the safety and ethical risks of using innovative solutions. This creates the need to develop ...
Added: December 7, 2025
Малинов С. А., Галактика медиа: журнал медиа исследований 2025 Т. 7 № 4 С. 154–173
In recent years, artificial intelligence (AI) has been actively integrated into everyday human life. Its popularity continues to grow steadily, and companies increasingly employ AI to optimize and accelerate workflows. Ordinary users leverage large language models (LLMs) and multimodal AI systems to perform a wide range of tasks, including generating texts, images, and videos; planning ...
Added: December 7, 2025
Komissarenko A., Voloshina E., Чевелева А. Н. et al., Scientific data 2025 Vol. 12 No. 1 Article 1687
Recently, the idea of brain-model alignment has been the topic of several influential works. However, most of previous studies were based on datasets collected during regular reading tasks where the subjects were not exposed to processing linguistic incongruencies, and stimuli were not controlled for key linguistic properties. Meanwhile, interpretability studies of Large Language Models pay ...
Added: November 18, 2025
Solovev G. V., Zhidkovskaya A. B., Orlova A. et al., , in: Findings of the Association for Computational Linguistics: EMNLP 2025.: Association for Computational Linguistics, 2025. Ch. 367 P. 6956–6998.
Hit identification is a central challenge in early drug discovery, traditionally requiring substantial experimental resources. Recent advances in artificial intelligence, particularly large language models (LLMs), have enabled virtual screening methods that reduce costs and improve efficiency. However, the growing complexity of these tools has limited their accessibility to wet-lab researchers. Multi-agent systems offer a promising ...
Added: November 16, 2025
Golyadkin M., Innokentiy Humonen, Rubanova V. et al., , in: MM '25: Proceedings of the 33rd ACM International Conference on Multimedia.: Association for Computing Machinery (ACM), 2025. P. 12875–12881.
We present the first multimodal dataset MuMMy, for developing research assistants that can interpret Egyptian hieroglyphic texts. It pairs images with Gardiner codes, transliteration, and English translation at two levels of granularity. We also evaluate several deep learning pipelines across OCR, transliteration, and translation tasks, revealing the complexity of the domain and the challenges posed ...
Added: November 8, 2025
Ignatenko V., Surkov A., Zakharov V. et al., Sci 2025 Vol. 7 No. 3 Article 130
Large language models (LLMs) have recently demonstrated remarkable capabilities in natural language processing, mathematical reasoning, and code generation. However, their potential for solving differential equations—fundamental to applied mathematics, physics, and engineering—remains insufficiently explored. For the first time, we applied LLMs as translators from the textual form of an equation into the textual representation of its ...
Added: October 10, 2025