Related papers: Word-Level Explanations for Analyzing Bias in Text…
User prompts for generative AI models are often underspecified, leading to a misalignment between the user intent and models' understanding. As a result, users commonly have to painstakingly refine their prompts. We study this alignment…
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…
Recent advances in text-to-image (T2I) generation have achieved impressive results, yet existing models still struggle with prompts that require rich world knowledge and implicit reasoning: both of which are critical for producing…
The issue of generative pretraining for vision models has persisted as a long-standing conundrum. At present, the text-to-image (T2I) diffusion model demonstrates remarkable proficiency in generating high-definition images matching textual…
Diffusion-based text-to-image (T2I) models enable high-quality image generation but also pose significant risks of misuse, particularly in producing not-safe-for-work (NSFW) content. While prior detection methods have focused on filtering…
The text-to-image synthesis by diffusion models has recently shown remarkable performance in generating high-quality images. Although performs well for simple texts, the models may get confused when faced with complex texts that contain…
Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. However, the advancement of T2I diffusion models presents significant risks, as the models could be…
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…
Generative AI leaderboards are central to evaluating model capabilities, but remain vulnerable to manipulation. Among key adversarial objectives is rank manipulation, where an attacker must first deanonymize the models behind displayed…
This paper investigates how popular text-to-image (T2I) models, DALL-E 3 and Gemini 3 Pro Preview, depict people from 206 nationalities when prompted to generate images of individuals engaging in common everyday activities. Five scenarios…
The ground truth used for training image, video, or speech quality prediction models is based on the Mean Opinion Scores (MOS) obtained from subjective experiments. Usually, it is necessary to conduct multiple experiments, mostly with…
Compositionality is a critical capability in Text-to-Image (T2I) models, as it reflects their ability to understand and combine multiple concepts from text descriptions. Existing evaluations of compositional capability rely heavily on…
Achieving precise word-level typography control within generated images remains a persistent challenge. To address it, we newly construct a word-level controlled scene text dataset and introduce the Text-Image Alignment (TIA) framework.…
Recent advancements in diffusion models have showcased their impressive capacity to generate visually striking images. Nevertheless, ensuring a close match between the generated image and the given prompt remains a persistent challenge. In…
Text-to-image diffusion models excel at generating high-quality, diverse images from natural language prompts. However, they often fail to produce semantically accurate results when the prompt contains concept combinations that contradict…
Text-to-image models are powerful for producing high-quality images based on given text prompts, but crafting these prompts often requires specialized vocabulary. To address this, existing methods train rewriting models with supervision…
Despite significant progress in generative AI, comprehensive evaluation remains challenging because of the lack of effective metrics and standardized benchmarks. For instance, the widely-used CLIPScore measures the alignment between a…
We present a comprehensive solution to learn and improve text-to-image models from human preference feedback. To begin with, we build ImageReward -- the first general-purpose text-to-image human preference reward model -- to effectively…
While large text-to-image models are able to synthesize "novel" images, these images are necessarily a reflection of the training data. The problem of data attribution in such models -- which of the images in the training set are most…
Text-to-image diffusion models have demonstrated remarkable capability in generating realistic images from arbitrary text prompts. However, they often produce inconsistent results for compositional prompts such as "two dogs" or "a penguin…