Related papers: Human Preference Score v2: A Solid Benchmark for E…

We present HumanEdit, a high-quality, human-rewarded dataset specifically designed for instruction-guided image editing, enabling precise and diverse image manipulations through open-form language instructions. Previous large-scale editing…

Large-scale text-to-image foundation models have achieved remarkable visual realism, yet generating human images with correct anatomical structures remains challenging. Existing approaches enforce anatomical constraints through…

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…

Recent advances in Score Distillation Sampling (SDS) have improved 3D human generation from textual descriptions. However, existing methods still face challenges in accurately aligning 3D models with long and complex textual inputs. To…

Deep generative models have shown impressive results in text-to-image synthesis. However, current text-to-image models often generate images that are inadequately aligned with text prompts. We propose a fine-tuning method for aligning such…

Computational inference of aesthetics is an ill-defined task due to its subjective nature. Many datasets have been proposed to tackle the problem by providing pairs of images and aesthetic scores based on human ratings. However, humans are…

The rapid advancement of text-to-image (T2I) models has increased the need for reliable human preference modeling, a demand further amplified by recent progress in reinforcement learning for preference alignment. However, existing…

Can Visual Language Models (VLMs) effectively capture human visual preferences? This work addresses this question by training VLMs to think about preferences at test time, employing reinforcement learning methods inspired by DeepSeek R1 and…

Deep generative models have the capacity to render high fidelity images of content like human faces. Recently, there has been substantial progress in conditionally generating images with specific quantitative attributes, like the emotion…

Capturing the diversity of people in images is challenging: recent literature tends to focus on diversifying one or two attributes, requiring expensive attribute labels or building classifiers. We introduce a diverse people image ranking…

Preference datasets are essential for training general-domain, instruction-following language models with Reinforcement Learning from Human Feedback (RLHF). Each subsequent data release raises expectations for future data collection,…

Human image generation is a key focus in image synthesis due to its broad applications, but even slight inaccuracies in anatomy, pose, or details can compromise realism. To address these challenges, we explore Direct Preference Optimization…

This paper presents an exploration of preference learning in text-to-motion generation. We find that current improvements in text-to-motion generation still rely on datasets requiring expert labelers with motion capture systems. Instead,…

Generative models have demonstrated remarkable capability in synthesizing high-quality text, images, and videos. For video generation, contemporary text-to-video models exhibit impressive capabilities, crafting visually stunning videos.…

Diffusion models have emerged as a dominant approach for text-to-image generation. Key components such as the human preference alignment and classifier-free guidance play a crucial role in ensuring generation quality. However, their…

Image and video synthesis has become a blooming topic in computer vision and machine learning communities along with the developments of deep generative models, due to its great academic and application value. Many researchers have been…

We present a novel multimodal preference dataset for creative tasks, consisting of over 250 million human ratings on more than 2.2 million captions, collected through crowdsourcing rating data for The New Yorker's weekly cartoon caption…

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,…

High-quality and open datasets remain a major bottleneck for text-to-image (T2I) fine-tuning. Despite rapid progress in model architectures and training pipelines, most publicly available fine-tuning datasets suffer from low resolution,…

The influence of textures on machine learning models has been an ongoing investigation, specifically in texture bias/learning, interpretability, and robustness. However, due to the lack of large and diverse texture data available, the…