publications

2026

MidSteer: Optimal Affine Framework for Steering Generative Models
Tatiana Gaintseva, Andrew Stepanov, Ziquan Liu, Martin Benning, Gregory Slabaugh, Jiankang Deng, Ismail Elezi
ICML 2026
[paper, GitHub]

Multi-Way Representation Alignment
Akshit Achara, Tatiana Gaintseva, Mateo Mahaut, Pritish Chakraborty, Viktor Stenby Johansson, Melih Barsbey, Emanuele Rodolà, Donato Crisostomi
ICML 2026
[paper, GitHub]

2025

CASteer: Steering Diffusion Models for Controllable Erasure
Tatiana Gaintseva, Andreea-Maria Oncescu, Chengcheng Ma, Ziquan Liu, Martin Benning, Gregory Slabaugh, Jiankang Deng, Ismail Elezi
ICLR 2026
[paper, GitHub]

2024

RAVE: Residual Vector Embedding for CLIP-Guided Backlit Image Enhancement
Tatiana Gaintseva, Martin Benning, Gregory Slabaugh
ECCV 2024
[paper, project page, GitHub]

Boundary detection in mixed AI-human texts
Laida Kushnareva, Tatiana Gaintseva, German Magai, Serguei Barannikov, Dmitry Abulkhanov, Kristian Kuznetsov, Eduard Tulchinskii, Irina Piontkovskaya, Sergey Nikolenko
COLM 2024, Outstanding Paper Award
[paper, GitHub]

Improving Interpretability and Robustness for the Detection of AI-Generated Images
Tatiana Gaintseva, Laida Kushnareva, German Magai, Irina Piontkovskaya, Sergey Nikolenko, Martin Benning, Serguei Barannikov, Gregory Slabaugh
arxiv preprint
[paper]

2020

Adaptive divergence for rapid adversarial optimization
Maxim Borisyak, Tatiana Gaintseva, and Andrey Ustyuzhanin
PeerJ Computer Science, 6, e274. 2020
[paper]