paper-with-me

Papers

DiffusionWorldViewer: Exposing and Broadening the Worldview Reflected by Generative Text-to-Image Models

2023-09-18 · Zoe De Simone, Angie Boggust, Arvind Satyanarayan, Ashia Wilson

Generative text-to-image (TTI) models produce high-quality images from short textual descriptions and are widely used in academic and creative domains. Like humans, TTI models have a worldview, a conception of the world learned from their training data and task that influences the images they generate for a given prompt. However, the worldviews of TTI models are often hidden from users, making it challenging for users to build intuition about TTI outputs, and they are often misaligned with users' worldviews, resulting in output images that do not match user expectations. In response, we introduce DiffusionWorldViewer, an interactive interface that exposes a TTI model's worldview across output demographics and provides editing tools for aligning output images with user perspectives. In a user study with 18 diverse TTI users, we find that DiffusionWorldViewer helps users represent their varied viewpoints in generated images and challenge the limited worldview reflected in current TTI models.

📄 PDF Abstract BibTeX arXiv:2309.09944

Code (1)

zoedesimone/diffusionworldviewer 공식 구현 pytorch

Tasks

Fairness

Methods 이 논문이 사용한 방법론

Focus 설명 없음
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

WorldView-Bench: A Benchmark for Evaluating Global Cultural Perspectives in Large Language Models

2025-05-14 · Abdullah Mushtaq, Imran Taj, Rafay Naeem, Ibrahim Ghaznavi 외

Large Language Models (LLMs) are predominantly trained and aligned in ways that reinforce Western-centric epistemologies and socio-cultural norms, leading to cultural homogenization and limiting their ability to reflect …

Benchmarking

Diffusion Models for Constrained Domains

2023-04-11 · Nic Fishman, Leo Klarner, Valentin De Bortoli, Emile Mathieu 외

Denoising diffusion models are a novel class of generative algorithms that achieve state-of-the-art performance across a range of domains, including image generation and text-to-image tasks. Building on this success, dif…

DenoisingImage GenerationProtein DesignUnconditional Image Generation

Avoiding Disparity Amplification under Different Worldviews

2018-08-26 · Samuel Yeom, Michael Carl Tschantz

We mathematically compare four competing definitions of group-level nondiscrimination: demographic parity, equalized odds, predictive parity, and calibration. Using the theoretical framework of Friedler et al., we study …

Fairness

Large Language Models Reflect the Ideology of their Creators

2024-10-24 · Maarten Buyl, Alexander Rogiers, Sander Noels, Guillaume Bied 외

Large language models (LLMs) are trained on vast amounts of data to generate natural language, enabling them to perform tasks like text summarization and question answering. These models have become popular in artificial…

Question AnsweringText Summarization

Reflected Schrödinger Bridge for Constrained Generative Modeling

2024-01-06 · Wei Deng, Yu Chen, Nicole Tianjiao Yang, Hengrong Du 외

Diffusion models have become the go-to method for large-scale generative models in real-world applications. These applications often involve data distributions confined within bounded domains, typically requiring ad-hoc …