1 citations · 2 across the 11 of their papers we have counts for
11 papers
When Activation Oracles Learn Not to Read: Concept-Specific Blind Spots in Fine-Tuned Oracles
Tobias Bersia, Tatiana Gaintseva
Activation Oracles (AOs) are language models trained to answer natural-language questions about another model's internal activations. They offer a flexible interface for reading hi…
EquiSteer: Cross-Attention Steering Towards a Fairer Text-Guided Image Generation
Tatiana Gaintseva, Akshit Achara, Gregory Slabaugh +2
Text-to-image diffusion models power everyday creative tasks, but they still reproduce the demographic biases in their training data. On common prompts such as ``a photo of a nurse…
A Geometric Account of Activation Steering through Angle-Norm Decomposition
Georgii Aparin, Tatiana Gaintseva
Linear activation steering has gained popularity as a simple and empirically effective way to control language model behavior. More recently, spherical steering paradigms have been…
MidSteer: Optimal Affine Framework for Steering Generative Models
Tatiana Gaintseva, Andrew Stepanov, Ziquan Liu +4
Steering intermediate representations has emerged as a powerful strategy for controlling generative models, particularly in post-deployment alignment and safety settings. However,…
SV-Detect: AI-generated Text Detection with Steering Vectors
Mikhail Vishnyakov, Tatiana Gaintseva
Detecting AI-generated text is especially difficult under distribution shift, such as transfer across domains, source models, and editing attacks. We propose an AI-generated text d…
Multi-Way Representation Alignment
Akshit Achara, Tatiana Gaintseva, Mateo Mahaut +5
The Platonic Representation Hypothesis suggests that independently trained neural networks converge to increasingly similar latent spaces. However, current strategies for mapping t…
CASteer: Cross-Attention Steering for Controllable Concept Erasure
Tatiana Gaintseva, Andreea-Maria Oncescu, Chengcheng Ma +5
Diffusion models have transformed image generation, yet controlling their outputs to reliably erase undesired concepts remains challenging. Existing approaches usually require task…
Improving Interpretability and Robustness for the Detection of AI-Generated Images
Tatiana Gaintseva, Laida Kushnareva, German Magai +5
With growing abilities of generative models, artificial content detection becomes an increasingly important and difficult task. However, all popular approaches to this problem suff…
RAVE: Residual Vector Embedding for CLIP-Guided Backlit Image Enhancement
Tatiana Gaintseva, Martin Benning, Gregory Slabaugh
In this paper we propose a novel modification of Contrastive Language-Image Pre-Training (CLIP) guidance for the task of unsupervised backlit image enhancement. Our work builds on…
AI-generated text boundary detection with RoFT
Laida Kushnareva, Tatiana Gaintseva, German Magai +6
Due to the rapid development of large language models, people increasingly often encounter texts that may start as written by a human but continue as machine-generated. Detecting t…
Adaptive Divergence for Rapid Adversarial Optimization
Maxim Borisyak, Tatiana Gaintseva, Andrey Ustyuzhanin
Adversarial Optimization (AO) provides a reliable, practical way to match two implicitly defined distributions, one of which is usually represented by a sample of real data, and th…