paper-with-me

Papers

Hacking Generative Models with Differentiable Network Bending

2023-10-07 · Giacomo Aldegheri, Alina Rogalska, Ahmed Youssef, Eugenia Iofinova

In this work, we propose a method to 'hack' generative models, pushing their outputs away from the original training distribution towards a new objective. We inject a small-scale trainable module between the intermediate layers of the model and train it for a low number of iterations, keeping the rest of the network frozen. The resulting output images display an uncanny quality, given by the tension between the original and new objectives that can be exploited for artistic purposes.

📄 PDF Abstract BibTeX arXiv:2310.04816

Code (1)

GAldegheri/gan-bending 공식 구현 pytorch

Similar Papers 제목 키워드 기반

BendTwin: Robust Dense-to-Sparse Physical Reconstruction with Bending-Aware Differentiable Spring-Mass Models

2026-08-06 · Yixiong Jing, Qi Wang, Lin Chen, Junwei Jiang 외 arxiv

Reconstructing objects with mechanical properties from video observations enables physically consistent dynamic prediction, benefiting robotics planning and interaction. Existing spring--mass based physical driven recons…

Network Bending of Diffusion Models for Audio-Visual Generation

2024-06-28 · Luke Dzwonczyk, Carmine Emanuele Cella, David Ban

In this paper we present the first steps towards the creation of a tool which enables artists to create music visualizations using pre-trained, generative, machine learning models. First, we investigate the application o…

Image Generation

Network Bending: Expressive Manipulation of Deep Generative Models

2020-05-25 · Terence Broad, Frederic Fol Leymarie, Mick Grierson

We introduce a new framework for manipulating and interacting with deep generative models that we call network bending. We present a comprehensive set of deterministic transformations that can be inserted as distinct lay…

Clustering

MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models

2025-10-02 · Kevin Zhai, Utsav Singh, Anirudh Thatipelli, Souradip Chakraborty 외 arxiv

Diffusion models excel at generating images conditioned on text prompts, but the resulting images often do not satisfy user-specific criteria measured by scalar rewards such as Aesthetic Scores. This alignment typically …

Explainability-in-Action: Enabling Expressive Manipulation and Tacit Understanding by Bending Diffusion Models in ComfyUI

2025-08-10 · Ahmed M. Abuzuraiq, Philippe Pasquier arxiv

Explainable AI (XAI) in creative contexts can go beyond transparency to support artistic engagement, modifiability, and sustained practice. While curated datasets and training human-scale models can offer artists greater…