研究人员正在开发新的基准和数据集，以推动文本到图像和文本到视频生成模型的发展。一篇论文介绍了GPIC，一个用于视觉生成的庞大、许可宽松的图像语料库，另一篇论文提出了用于评估长篇、复杂文本到视频生成的LoCoT2V-Bench。此外，新的方法正在出现，用于评估文本到图像模型的公平性和对齐性，以及提高离散文本到图像生成的效率和质量。 AI
影响 新的数据集和评估框架将加速多模态人工智能生成的研究和开发，推动图像和视频合成的界限。
排序理由 多篇研究论文介绍了人工智能生成任务的新数据集、基准和评估方法。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 37 个来源。 我们如何撰写摘要 →
arXiv:2503.07265v4 Announce Type: replace-cross Abstract: Text-to-Image (T2I) models are capable of generating high-quality artistic creations and visual content. However, existing research and evaluation standards predominantly focus on image realism and shallow text-image align…
arXiv:2606.01282v1 Announce Type: cross Abstract: Text-to-Image (TTI) systems are now everyday infrastructure for journalism, education, advertising, and public communication, and the demographic and cultural stereotypes they inherit from training data (rendering women, people of…
arXiv:2605.30341v1 Announce Type: cross Abstract: Studying scalable methods for visual generative modeling requires large, accessible, and stable datasets. We introduce GPIC, a Giant Permissive Image Corpus of approximately 28 trillion pixels. GPIC comprises diverse internet imag…
arXiv:2510.26412v3 Announce Type: replace-cross Abstract: Recent advances in text-to-video generation have achieved impressive performance on short clips, yet evaluating long-form generation under complex textual inputs remains a significant challenge. In response to this challen…
arXiv:2605.29476v1 Announce Type: new Abstract: This work presents a comparative evaluation of machine translation systems applied to images containing textual information, a task that lies at the intersection of computer vision and natural language processing. The study compares…
Studying scalable methods for visual generative modeling requires large, accessible, and stable datasets. We introduce GPIC, a Giant Permissive Image Corpus of approximately 28 trillion pixels. GPIC comprises diverse internet images captioned by a state-of-the-art vision-language…
arXiv:2605.26332v1 Announce Type: cross Abstract: Machine unlearning aims to remove specific concepts from pretrained text-to-image diffusion models, yet several white- and black-box attacks have been introduced to make the model generate such unlearned concepts. These attacks, n…
arXiv:2505.23606v5 Announce Type: replace Abstract: Unified generation models aim to handle diverse tasks across modalities -- such as text generation, image generation, and vision-language reasoning -- within a single architecture and decoding paradigm. Autoregressive unified mo…
BiDPO enhances text-to-image models for complex compositional prompts through preference-based fine-tuning and region-level guidance.
arXiv:2510.22827v3 Announce Type: replace-cross Abstract: Evaluating text-to-image (T2I) systems requires judging not only whether an image matches a prompt, but also whether socially salient attributes are represented faithfully and without unsupported inference. Existing automa…
With the continued advancement of text-to-image (T2I) generation, producing high-quality images is becoming increasingly attainable; consequently, user demands are shifting toward images that better satisfy their specific requirements. As reward models play an increasingly import…
Lens is a compact 3.8B-parameter text-to-image model achieving superior performance with reduced training compute through dense caption datasets, multi-resolution batching, efficient architecture, and optimization techniques.
Discrete autoregressive text-to-image models suffer from latent covariate shift during policy optimization, which RankE addresses through end-to-end co-evolution of policy and decoder components.
arXiv:2606.05829v1 Announce Type: new Abstract: Artistic styles are rooted in specific socio-historical contexts that encode social hierarchies, including distinct constructions of gender. Yet in AI research, style has long been treated as a surface-level visual property: a filte…
Artistic styles are rooted in specific socio-historical contexts that encode social hierarchies, including distinct constructions of gender. Yet in AI research, style has long been treated as a surface-level visual property: a filter of color, brushstroke, and texture applied to …
arXiv:2606.04264v1 Announce Type: new Abstract: Recent years have seen remarkable progress in unified vision-language models handling both multimodal understanding and generation within a single architecture. While autoregressive VLMs can reason across modalities, they fail to ge…
arXiv:2606.03243v1 Announce Type: new Abstract: Modern text-to-image models have achieved strong visual synthesis, yet remain unreliable when prompts require implicit visual constraints, relational reasoning, or external knowledge. Existing retrieval-augmented and agentic generat…
arXiv:2606.03715v1 Announce Type: new Abstract: Text-to-image models rely on text prompts as their primary interface to human intent. Prompts are encoded by a text encoder into embeddings that condition the image generation process. Beyond individual token meanings, text embeddin…
Text-to-image models rely on text prompts as their primary interface to human intent. Prompts are encoded by a text encoder into embeddings that condition the image generation process. Beyond individual token meanings, text embeddings encode contextual information across the full…
arXiv:2507.02792v5 Announce Type: replace Abstract: Text-to-image (T2I) diffusion models have shown remarkable success in generating high-quality images from text prompts. Recent efforts extend these models to incorporate conditional images (e.g., canny edge) for fine-grained spa…
arXiv:2412.03876v2 Announce Type: replace Abstract: Text-to-Image (T2I) diffusion models are widely recognized for their ability to generate high-quality and diverse images based on text prompts. However, despite recent advances, these models are still prone to generating unsafe …
arXiv:2605.29390v1 Announce Type: new Abstract: Text-to-image (T2I) models have become increasingly capable of generating high-quality images. Yet, enforcing the explicit absence of a specified object or attribute remains a fundamentally challenging problem. Existing approaches, …
arXiv:2512.01334v2 Announce Type: replace Abstract: Text-guided image-to-video generation has made substantial progress, yet it still struggles to execute text-specified edits that require substantial changes to a reference image (\textit{e.g., object addition, removal, or modifi…
arXiv:2604.03799v2 Announce Type: replace Abstract: Autoregressive (AR) models offer stable and efficient training, but standard next-token prediction is not well aligned with the temporal structure required for text-conditioned motion generation. We introduce MoScale, a next-sca…
arXiv:2605.28615v1 Announce Type: new Abstract: 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 th…
arXiv:2605.28091v1 Announce Type: new Abstract: 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 …
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 propose BiDPO, a framework to enhance T2I…
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 real-world reconstruction and genuine creative e…
arXiv:2605.12271v2 Announce Type: replace Abstract: Humans often specify and create through visual artifacts: typography sheets, sketches, reference images, and annotated scenes. Yet modern visual generators still ask users to serialize this intent into text, a bottleneck that co…
arXiv:2605.25876v1 Announce Type: new Abstract: With the continued advancement of text-to-image (T2I) generation, producing high-quality images is becoming increasingly attainable; consequently, user demands are shifting toward images that better satisfy their specific requiremen…
arXiv:2605.25763v1 Announce Type: new Abstract: Text-to-image synthesis has made significant progress, benefiting from the strong generative capabilities of diffusion models. However, these models struggle to achieve precise text-to-image alignment within cross-attention maps dur…
arXiv:2503.01122v2 Announce Type: replace Abstract: Image personalization has garnered attention for its ability to customize Text-to-Image generation using only a few reference images. However, a key challenge in image personalization is the issue of conceptual coupling, where t…
With the continued advancement of text-to-image (T2I) generation, producing high-quality images is becoming increasingly attainable; consequently, user demands are shifting toward images that better satisfy their specific requirements. As reward models play an increasingly import…
Text-to-image synthesis has made significant progress, benefiting from the strong generative capabilities of diffusion models. However, these models struggle to achieve precise text-to-image alignment within cross-attention maps during the denoising process. Existing works primar…
arXiv:2503.06684v3 Announce Type: replace Abstract: Recent advances in diffusion-based text-to-image generation have demonstrated promising results through visual condition control. However, existing ControlNet-like methods struggle with compositional visual conditioning - simult…
arXiv:2605.21573v1 Announce Type: new Abstract: We introduce Lens, a 3.8B-parameter T2I model that achieves performance competitive with, and in several cases surpassing, state-of-the-art models with more than 6B parameters across various benchmarks, while requiring significantly…
Discrete autoregressive (AR) text-to-image (T2I) models pair a VQ tokenizer with an AR policy, and current post-training pipelines optimize only the policy while keeping the VQ decoder frozen. Recent diffusion T2I work, exemplified by REPA-E, has shown that the VAE itself constit…