Related papers: Position: Universal Aesthetic Alignment Narrows Ar…
Recent studies show that deep vision-only and language-only models--trained on disjoint modalities--nonetheless project their inputs into a partially aligned representational space. Yet we still lack a clear picture of where in each network…
Rating how aesthetically pleasing an image appears is a highly complex matter and depends on a large number of different visual factors. Previous work has tackled the aesthetic rating problem by ranking on a 1-dimensional rating scale,…
It is tempting to think that machines are less prone to unfairness and prejudice. However, machine learning approaches compute their outputs based on data. While biases can enter at any stage of the development pipeline, models are…
Recent advancements in artificial intelligence (AI) have broadened the applicability of AI-generated images across various sectors, including the creative industry and design. However, their utilization in educational contexts, particularly…
How to robustly rank the aesthetic quality of given images has been a long-standing ill-posed topic. Such challenge stems mainly from the diverse subjective opinions of different observers about the varied types of content. There is a…
Image aesthetic assessment (IAA) aims to predict the aesthetic quality of images as perceived by humans. While recent IAA models achieve strong predictive performance, they offer little insight into the factors driving their predictions.…
There are not one but two dimensions of bias that can be revealed through the study of large AI models: not only bias in training data or the products of an AI, but also bias in society, such as disparity in employment or health outcomes…
This study investigates the aesthetic experience and educational value of collaborative artmaking with generative artificial intelligence (AI) among young learners and art students. Based on a survey of 112 participants, we examine how…
Affective alignment in generative AI represents a systemic risk to the developmental autonomy of younger users. Although emotional mirroring is commonly seen as a hallmark of advanced human-machine interaction, it can also manifest as…
Graphic layout is essential in poster generation. Professionals often need to design different layouts for a product image, to ensure they meet specific user requirements. This paper focuses on utilizing a deep-learning model to…
Reward modeling has emerged as a crucial component in aligning large language models with human values. Significant attention has focused on using reward models as a means for fine-tuning generative models. However, the reward models…
Visual aesthetic assessment has been an active research field for decades. Although latest methods have achieved promising performance on benchmark datasets, they typically rely on a large number of manual annotations including both…
The cost of error in many high-stakes settings is asymmetric: misdiagnosing pneumonia when absent is an inconvenience, but failing to detect it when present can be life-threatening. Because of this, artificial intelligence (AI) models used…
General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. The problem is not only that models fail on edge cases; it is that current evaluation makes…
Image generation models can generate or edit images from a given text. Recent advancements in image generation technology, exemplified by DALL-E and Midjourney, have been groundbreaking. These advanced models, despite their impressive…
We study a systematic bias in modern image generation models: the mention order of entities in text spuriously determines spatial layout and entity--role binding. We term this phenomenon Order-to-Space Bias (OTS) and show that it arises in…
This paper examines algorithmic lookism-the systematic preferential treatment based on physical appearance-in text-to-image (T2I) generative AI and a downstream gender classification task. Through the analysis of 26,400 synthetic faces…
We explore computational approaches for visual guidance to aid in creating aesthetically pleasing art and graphic design. Our work complements and builds on previous work that developed models for how humans look at images. Our approach…
Text-to-image models are enabling efficient design space exploration, rapidly generating images from text prompts. However, many generative AI tools are imperfect for product design applications as they are not built for the goals and…
Inferring reward functions from human behavior is at the center of value alignment - aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of…