Dmitrii Tarasov

According to our database, Dmitrii Tarasov authored at least 6 papers between 2025 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Towards Robust Speech Deepfake Detection via Human-Inspired Reasoning.

Artem Dvirniak, Evgeny Kushnir, Dmitrii Tarasov, Artyom Iudin, Oleg Kiriukhin, Mikhail Pautov, Dmitrii Korzh, Oleg Y. Rogov

CoRR, March, 2026

Feature Inversion as a Lens on Vision Encoders.

Eduard Allakhverdov, Dmitrii Tarasov, Elizaveta Goncharova, Andrey Kuznetsov

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2026

2025

Sentence-Anchored Gist Compression for Long-Context LLMs.

Dmitrii Tarasov, Elizaveta Goncharova, Andrey Kuznetsov

CoRR, November, 2025

Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences.

Dmitrii Korzh, Dmitrii Tarasov, Artyom Iudin, Elvir Karimov, Matvey Skripkin, Nikita Kuzmin, Andrey Kuznetsov, Oleg Y. Rogov, Ivan V. Oseledets

CoRR, August, 2025

Image Reconstruction as a Tool for Feature Analysis.

Eduard Allakhverdov, Dmitrii Tarasov, Elizaveta Goncharova, Andrey Kuznetsov

CoRR, June, 2025

MOVE: A Mixture-of-Vision-Encoders Approach for Domain-Focused Vision-Language Processing.

Matvey Skripkin, Elizaveta Goncharova, Dmitrii Tarasov, Andrey Kuznetsov

CoRR, February, 2025