collaborators

6 papers

cs.CL2026

SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens

Nikita Dragunov, Temurbek Rahmatullaev, Elizaveta Goncharova +5

The recently proposed Large Concept Model (LCM) generates text by predicting a sequence of sentence-level embeddings and training with either mean-squared error or diffusion object…

cs.AI2026

NoReGeo: Non-Reasoning Geometry Benchmark

Irina Abdullaeva, Anton Vasiliuk, Elizaveta Goncharova +4

We present NoReGeo, a novel benchmark designed to evaluate the intrinsic geometric understanding of large language models (LLMs) without relying on reasoning or algebraic computati…

cs.AI2025

Universal Adversarial Attack on Aligned Multimodal LLMs

Temurbek Rahmatullaev, Polina Druzhinina, Nikita Kurdiukov +3

We propose a universal adversarial attack on multimodal Large Language Models (LLMs) that leverages a single optimized image to override alignment safeguards across diverse queries…

math.GR2025

On consecutive factors of the lower central series of right-angled Coxeter groups

Yakov Veryovkin, Temur Rahmatullaev

We study the lower central series of the right-angled Coxeter group and the corresponding associated graded Lie algebra and describe the basis of…

cs.CL2025

LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers

Anton Razzhigaev, Matvey Mikhalchuk, Temurbek Rahmatullaev +4

We introduce methods to quantify how Large Language Models (LLMs) encode and store contextual information, revealing that tokens often seen as minor (e.g., determiners, punctuation…

math.AT2025

Polyhedral products, graph products and p-central series

Taras Panov, Temurbek Rahmatullaev

We relate polyhedral products of topological spaces to graph products of groups. The loop homology algebras of polyhedral products are identified with the universal enveloping alge…