相关论文: Embedding an Ethical Mind: Aligning Text-to-Image …

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 models have become a central paradigm for image and multimodal generation, yet their deployment raises persistent questions about alignment, safety, preference satisfaction, and robustness to misuse. This survey reviews recent…

Video diffusion models (VDMs) have demonstrated remarkable capabilities in text-to-video (T2V) generation. Despite their success, VDMs still suffer from degraded image quality and flickering artifacts. To address these issues, some…

As text-to-image models grow increasingly powerful and complex, their burgeoning size presents a significant obstacle to widespread adoption, especially on resource-constrained devices. This paper presents a pioneering study on…

Although text-to-image (T2I) models have recently thrived as visual generative priors, their reliance on high-quality text-image pairs makes scaling up expensive. We argue that grasping the cross-modality alignment is not a necessity for a…

Recently, diffusion models have been proven to perform remarkably well in text-to-image synthesis tasks in a number of studies, immediately presenting new study opportunities for image generation. Google's Imagen follows this research trend…

This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task to simultaneously a) accomplish the synthesis of…

Although Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, they encounter challenges in terms of reasoning efficiency, large model size and overthinking. However, existing lightweight…

Diffusion models have achieved impressive success in generating photorealistic images, but challenges remain in ensuring precise semantic alignment with input prompts. Optimizing the initial noisy latent offers a more efficient alternative…

Progress in Text-to-Image (T2I) models has significantly improved the generation of images from textual descriptions. However, existing evaluation metrics do not adequately assess the models' ability to handle a diverse range of textual…

Text-conditioned image-to-video generation (TI2V) aims to synthesize a realistic video starting from a given image (e.g., a woman's photo) and a text description (e.g., "a woman is drinking water."). Existing TI2V frameworks often require…

Text-driven Image to Video Generation (TI2V) aims to generate controllable video given the first frame and corresponding textual description. The primary challenges of this task lie in two parts: (i) how to identify the target objects and…

Text-to-image (T2I) diffusion models generate high-quality images but often fail to capture the spatial relations specified in text prompts. This limitation can be traced to two factors: lack of fine-grained spatial supervision in training…

Text-to-video (T2V) generation technology holds potential to transform multiple domains such as education, marketing, entertainment, and assistive technologies for individuals with visual or reading comprehension challenges, by creating…

Text-to-image (T2I) models achieve high-fidelity generation through extensive training on large datasets. However, these models may unintentionally pick up undesirable biases of their training data, such as over-representation of particular…

Text-to-image diffusion models have recently emerged at the forefront of image generation, powered by very large-scale unsupervised or weakly supervised text-to-image training datasets. Due to their unsupervised training, controlling their…

Preference optimization for diffusion models aims to align them with human preferences for images. Previous methods typically use Vision-Language Models (VLMs) as pixel-level reward models to approximate human preferences. However, when…

Recent progress in diffusion models has revolutionized the popular technology of text-to-image generation. While existing approaches could produce photorealistic high-resolution images with text conditions, there are still several open…

This paper explores a novel lightweight approach LightFair to achieve fair text-to-image diffusion models (T2I DMs) by addressing the adverse effects of the text encoder. Most existing methods either couple different parts of the diffusion…

Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has…