Related papers: DesignSense: A Human Preference Dataset and Reward…

Graphic design is essential for visual communication with layouts being fundamental to composing attractive designs. Layout generation differs from pixel-level image synthesis and is unique in terms of the requirement of mutual relations…

Visual layouts are essential in graphic design fields such as advertising, posters, and web interfaces. The application of generative models for content-aware layout generation has recently gained traction. However, these models fail to…

Conditional graphic layout generation, which automatically maps user constraints to high-quality layouts, has attracted widespread attention today. Although recent works have achieved promising performance, the lack of versatility and data…

While there has been remarkable progress in the performance of visual recognition algorithms, the state-of-the-art models tend to be exceptionally data-hungry. Large labeled training datasets, expensive and tedious to produce, are required…

Visual Quality Assessment (QA) seeks to predict human perceptual judgments of visual fidelity. While recent multimodal large language models (MLLMs) show promise in reasoning about image and video quality, existing approaches mainly rely on…

Attaining a high degree of user controllability in visual generation often requires intricate, fine-grained inputs like layouts. However, such inputs impose a substantial burden on users when compared to simple text inputs. To address the…

Large Language Models (LLMs) have achieved remarkable success across diverse natural language tasks, yet the reward models employed for aligning LLMs often encounter challenges of reward hacking, where the approaches predominantly rely on…

Vision-language generative reward models (VL-GenRMs) play a crucial role in aligning and evaluating multimodal AI systems, yet their own evaluation remains under-explored. Current assessment methods primarily rely on AI-annotated preference…

Preference learning is critical for aligning large language models (LLMs) with human values, with the quality of preference datasets playing a crucial role in this process. While existing metrics primarily assess data quality based on…

Designing visually appealing layouts for multimedia documents containing text, graphs and images requires a form of creative intelligence. Modelling the generation of layouts has recently gained attention due to its importance in aesthetics…

Recently, we have witnessed great progress in image editing with natural language instructions. Several closed-source models like GPT-Image-1, Seedream, and Google-Nano-Banana have shown highly promising progress. However, the open-source…

Human preference evaluations are widely used to compare generative models, yet it remains unclear how many judgments are required to reliably detect small improvements. We show that when preference signal is diffuse across prompts (i.e.,…

Recent generative models have significantly advanced speech restoration tasks, yet their training objectives often misalign with human perceptual preferences, resulting in suboptimal quality. While post-training alignment has proven…

We introduce ImageGem, a dataset for studying generative models that understand fine-grained individual preferences. We posit that a key challenge hindering the development of such a generative model is the lack of in-the-wild and…

Ensuring native-like quality of large language model (LLM) responses across many languages is challenging. To address this, we introduce MENLO, a framework that operationalizes the evaluation of native-like response quality based on…

The rapid evolution of Large Language Models (LLMs) has fostered diverse paradigms for automated slide generation, ranging from code-driven layouts to image-centric synthesis. However, evaluating these heterogeneous systems remains…

Evaluating concept customization is challenging, as it requires a comprehensive assessment of fidelity to generative prompts and concept images. Moreover, evaluating multiple concepts is considerably more difficult than evaluating a single…

Aligning large language models (LLMs) to human preferences is challenging in domains where preference data is unavailable. We address the problem of learning reward models for such target domains by leveraging feedback collected from…

Recent advancements in Large Language Models (LLMs) have been remarkable, with new models consistently surpassing their predecessors. These advancements are underpinned by extensive research on various training mechanisms. Among these,…

3D content creation from text prompts has shown remarkable success recently. However, current text-to-3D methods often generate 3D results that do not align well with human preferences. In this paper, we present a comprehensive framework,…