Related papers: DesignPref: Capturing Personal Preferences in Visu…

Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values. While benchmarks for general response…

Generative AI (GenAI) tools are increasingly integrated into design workflows. While text prompts remain the primary input method for GenAI image tools, designers often struggle to craft effective ones. Moreover, research has primarily…

Recent advances in human preference alignment have significantly improved multimodal generation and understanding. A key approach is to train reward models that provide supervision signals for preference optimization. However, existing…

Learning from preference feedback is essential for aligning large language models (LLMs) with human values and improving the quality of generated responses. However, existing preference learning methods rely heavily on curated data from…

Alignment algorithms are widely used to align large language models (LLMs) to human users based on preference annotations. Typically these (often divergent) preferences are aggregated over a diverse set of users, resulting in fine-tuned…

Modern text-to-image (T2I) models generate high-fidelity visuals but remain indifferent to individual user preferences. While existing reward models optimize for "average" human appeal, they fail to capture the inherent subjectivity of…

Generative AI (GenAI) models have become more capable than ever at augmenting productivity and cognition across diverse contexts. However, a fundamental challenge remains as users struggle to anticipate what AI will generate. As a result,…

Large language models (LLMs) have traditionally been aligned through one-size-fits-all approaches that assume uniform human preferences, fundamentally overlooking the diversity in user values and needs. This paper introduces a comprehensive…

Large Language Models (LLMs) are increasingly used as chatbots, yet their ability to personalize responses to user preferences remains limited. We introduce PrefEval, a benchmark for evaluating LLMs' ability to infer, memorize and adhere to…

In this paper, we examine the visual variability of objects across different ad categories, i.e. what causes an advertisement to be visually persuasive. We focus on modeling and generating faces which appear to come from different types of…

The use of computational methods to evaluate aesthetics in photography has gained interest in recent years due to the popularization of convolutional neural networks and the availability of new annotated datasets. Most studies in this area…

Visual attributes, which refer to human-labeled semantic annotations, have gained increasing popularity in a wide range of real world applications. Generally, the existing attribute learning methods fall into two categories: one focuses on…

In the fields of Experimental and Computational Aesthetics, numerous image datasets have been created over the last two decades. In the present work, we provide a comparative overview of twelve image datasets that include aesthetic ratings…

Generative AI systems have been heralded as tools for augmenting human creativity and inspiring divergent thinking, though with little empirical evidence for these claims. This paper explores the effects of exposure to AI-generated images…

Preference alignment aims to guide generative models by learning from comparisons between preferred and non-preferred samples. In practice, most existing approaches rely on preference pairs constructed from model-generated images. Such…

Recent advancements have brought generated music closer to human-created compositions, yet evaluating these models remains challenging. While human preference is the gold standard for assessing quality, translating these subjective…

Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including…

Modern recommender systems model people and items by discovering or `teasing apart' the underlying dimensions that encode the properties of items and users' preferences toward them. Critically, such dimensions are uncovered based on user…

With the success of image generation, generative diffusion models are increasingly adopted for discriminative tasks, as pixel generation provides a unified perception interface. However, directly repurposing the generative denoising process…

Despite significant advances in large language models, personalizing them for individual decision-makers remains an open problem. Here, we introduce a synthetic-organic supervision pipeline that transforms raw judicial decisions into…