activity
20242026
collaborators

5 papers

physics.soc-ph2026

Topological measures in weighted hypergraphs

Ekaterina Vasilyeva, Liubov Tupikina, Daniil Musatov +3

Higher-order interactions introduce an additional structural dimension to complex networks, requiring consistent generalizations of classical topological measures. In hypergraphs,…

cs.CL2026

Thinking Before Constraining: A Unified Decoding Framework for Large Language Models

Ngoc Trinh Hung Nguyen, Alonso Silva, Laith Zumot +3

Natural generation allows Large Language Models (LLMs) to produce free-form responses with rich reasoning, yet the lack of structure makes outputs difficult to verify. Conversely,…

cs.SI2025

Iterative Ricci-Foster Curvature Flow with GMM-Based Edge Pruning: A Novel Approach to Community Detection

Arsenii Onuchin, Konstantin Sorokin, Maxim Beketov +1

Community detection in complex networks is a fundamental problem, open to new approaches in various scientific settings. We introduce a novel community detection method, based on R…

cs.LG2025

Two-dimensional Taxonomy for N-ary Knowledge Representation Learning Methods

Xiaohua Lu, Liubov Tupikina, Mehwish Alam

Real-world knowledge can take various forms, including structured, semi-structured, and unstructured data. Among these, knowledge graphs are a form of structured human knowledge th…

cs.LG2024

Dissecting embedding method: learning higher-order structures from data

Liubov Tupikina, Kathuria Hritika

Active area of research in AI is the theory of manifold learning and finding lower-dimensional manifold representation on how we can learn geometry from data for providing better q…