Related papers: DEsignBench: Exploring and Benchmarking DALL-E 3 f…
Recent breakthroughs in large multimodal models (LMMs) have significantly advanced both text-to-image (T2I) generation and image-to-text (I2T) interpretation. However, many generated images still suffer from issues related to perceptual…
The ability to understand visual concepts and replicate and compose these concepts from images is a central goal for computer vision. Recent advances in text-to-image (T2I) models have lead to high definition and realistic image quality…
Recent advances in generative AI have enabled visual content creation through text-to-image (T2I) generation. However, despite their creative potential, T2I models often replicate and amplify societal stereotypes -- particularly those…
While text-to-image (T2I) generative models have become ubiquitous, they do not necessarily generate images that align with a given prompt. While previous work has evaluated T2I alignment by proposing metrics, benchmarks, and templates for…
The rapid advancement of generative models, such as GANs and Diffusion models, has enabled the creation of highly realistic synthetic images, raising serious concerns about misinformation, deepfakes, and copyright infringement. Although…
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…
Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align…
Despite advancements in text-to-image generation (T2I), prior methods often face text-image misalignment problems such as relation confusion in generated images. Existing solutions involve cross-attention manipulation for better…
DevBench is a telemetry-driven benchmark designed to evaluate Large Language Models (LLMs) on realistic code completion tasks. It includes 1,800 evaluation instances across six programming languages and six task categories derived from real…
This paper explores the feasibility of using text-to-image models in a zero-shot setup to generate images for taxonomy concepts. While text-based methods for taxonomy enrichment are well-established, the potential of the visual dimension…
Text-to-video (T2V) generative models have advanced significantly, yet their ability to compose different objects, attributes, actions, and motions into a video remains unexplored. Previous text-to-video benchmarks also neglect this…
Recent advances in text-to-image (T2I) models have achieved impressive quality and consistency. However, this has come at the cost of representation diversity. While automatic evaluation methods exist for benchmarking model diversity, they…
Text-to-image (T2I) diffusion models are popular for introducing image manipulation methods, such as editing, image fusion, inpainting, etc. At the same time, image-to-video (I2V) and text-to-video (T2V) models are also built on top of T2I…
Text-to-Image (T2I) models have recently gained significant attention due to their ability to generate high-quality images and are consequently used in a wide range of applications. However, there are concerns about the gender bias of these…
Accurate interpretation and visualization of human instructions are crucial for text-to-image (T2I) synthesis. However, current models struggle to capture semantic variations from word order changes, and existing evaluations, relying on…
In this work, we reveal the limitations of visual tokenizers and VAEs in preserving fine-grained features, and propose a benchmark to evaluate reconstruction performance for two challenging visual contents: text and face. Visual tokenizers…
We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…
Text-conditioned image generation has gained significant attention in recent years and are processing increasingly longer and comprehensive text prompt. In everyday life, dense and intricate text appears in contexts like advertisements,…
Regional defaults describe the emerging phenomenon that text-to-image (T2I) foundation models used in generative AI are prone to over-proportionally depicting certain geographic regions to the exclusion of others. In this work, we introduce…
Text-to-video (T2V) models have shown remarkable performance in generating visually reasonable scenes, while their capability to leverage world knowledge for ensuring semantic consistency and factual accuracy remains largely understudied.…