collaborators

7 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.CL2026

Logit-KL Flow Matching: Non-Autoregressive Text Generation via Sampling-Hybrid Inference

Egor Sevriugov, Nikita Dragunov, Anton Razzhigaev +2

Non-autoregressive (NAR) language models offer notable efficiency in text generation by circumventing the sequential bottleneck of autoregressive decoding. However, accurately mode…

cs.CL2025

MindShift: Analyzing Language Models' Reactions to Psychological Prompts

Anton Vasiliuk, Irina Abdullaeva, Polina Druzhinina +2

Large language models (LLMs) hold the potential to absorb and reflect personality traits and attitudes specified by users. In our study, we investigated this potential using robust…

cs.CV2025

Real-World Transferable Adversarial Attack on Face-Recognition Systems

Andrey Kaznacheev, Matvey Mikhalchuk, Andrey Kuznetsov +2

Adversarial attacks on face recognition (FR) systems pose a significant security threat, yet most are confined to the digital domain or require white-box access. We introduce GaP (…

cs.CV2025

Inverting Black-Box Face Recognition Systems via Zero-Order Optimization in Eigenface Space

Anton Razzhigaev, Matvey Mikhalchuk, Klim Kireev +3

Reconstructing facial images from black-box recognition models poses a significant privacy threat. While many methods require access to embeddings, we address the more challenging…

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…