Martin Benning — accepted AI-conference papers

2026

CASteer: Cross-Attention Steering for Controllable Concept Erasure

Tatiana Gaintseva, Andreea-Maria Oncescu, Chengcheng Ma, Ziquan Liu, Martin Benning, Gregory Slabaugh +2

ICLR 2026poster

Diffusion models have transformed image generation, yet controlling their outputs for diverse applications, including content moderation and creative customization, remains challenging. Existing approaches usually require task-specific training and struggle to generalise across both concrete (e.g.,…

Cited by 0 Source ↗code ↗Scholar ↗

2026

MIDSTEER: Optimal Affine Framework for Steering Generative Models

Tatiana Gaintseva, Andrew Stepanov, Ziquan Liu, Martin Benning, Gregory Slabaugh, Jiankang Deng +1

ICML 2026poster

Steering intermediate representations has emerged as a powerful strategy for controlling generative models. However, despite its empirical success, it currently lacks a comprehensive theoretical framework. In this paper, we bridge this gap by formalizing the theory of concept steering. First, we est…

Cited by 0 Source ↗Scholar ↗

2024

RAVE: Residual Vector Embedding for CLIP-Guided Backlit Image Enhancement

Tatiana Gaintseva*, Martin Benning, Gregory Slabaugh*

ECCV 2024poster

"In this paper we propose a novel modification of Contrastive Language-Image Pre-Training (CLIP) guidance for the task of backlit image enhancement. Our work builds on the state-of-the-art CLIP-LIT approach, which learns a prompt pair by constraining the text-image similarity between a prompt (negat…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗