Related papers: ImageDoctor: Diagnosing Text-to-Image Generation v…

Recent advances in text-to-image (T2I) generation via reinforcement learning (RL) have benefited from reward models that assess semantic alignment and visual quality. However, most existing reward models pay limited attention to…

Text-to-Image generation has evolved from basic image synthesis into a frequently used core capability in professional creative workflows, where simple text-image alignment can no longer satisfy users' pressing demands for faithful…

Reasoning is a fundamental capability often required in real-world text-to-image (T2I) generation, e.g., generating ``a bitten apple that has been left in the air for more than a week`` necessitates understanding temporal decay and…

Recent text-to-image (T2I) diffusion and flow-matching models can produce highly realistic images from natural language prompts. In practical scenarios, T2I systems are often run in a ``generate--then--select'' mode: many seeds are sampled…

Diffusion models have emerged as a dominant paradigm for generative modeling across a wide range of domains, including prompt-conditional generation. The vast majority of samplers, however, rely on forward discretization of the reverse…

In spite of recent progress, image diffusion models still produce artifacts. A common solution is to leverage the feedback provided by quality assessment systems or human annotators to optimize the model, where images are generally rated in…

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…

Evaluating the alignment between textual prompts and generated images is critical for ensuring the reliability and usability of text-to-image (T2I) models. However, most existing evaluation methods rely on coarse-grained metrics or static…

With the rapid advancement of text-to-image (T2I) generation models, assessing the semantic alignment between generated images and text descriptions has become a significant research challenge. Current methods, including those based on…

Despite the rapid progress of text-to-image (T2I) models, generating images that accurately reflect complex compositional prompts (covering attribute bindings, object relationships, counting) still remains challenging. To address this, we…

Recently, Text-to-Image (T2I) generation models have achieved significant advancements. Correspondingly, many automated metrics have emerged to evaluate the image-text alignment capabilities of generative models. However, the performance…

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…

Recent text-guided image editing (TIE) models have achieved remarkable progress, however, many edited results still suffer from artifacts, unintended modifications, and suboptimal aesthetics. Although several benchmarks and evaluation…

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…

Recent text-to-image (T2I) models have made remarkable progress in generating visually realistic and semantically coherent images. However, they still suffer from randomness and inconsistency with the given prompts, particularly when…

Contemporary image generation systems have achieved high fidelity and superior aesthetic quality beyond basic text-image alignment. However, existing evaluation frameworks have failed to evolve in parallel. This study reveals that human…

Evaluating the quality of automatically generated image descriptions is a complex task that requires metrics capturing various dimensions, such as grammaticality, coverage, accuracy, and truthfulness. Although human evaluation provides…

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…

Contemporary Text-to-Image (T2I) models frequently depend on qualitative human evaluations to assess the consistency between synthesized images and the text prompts. There is a demand for quantitative and automatic evaluation tools, given…

Visual generative models have achieved remarkable progress in synthesizing photorealistic images and videos, yet aligning their outputs with human preferences across critical dimensions remains a persistent challenge. Though reinforcement…