Related papers: SCHEMA for Gemini 3 Pro Image: A Structured Method…

Recent multimodal image generators such as GPT-4o, Gemini 2.0 Flash, and Gemini 2.5 Pro excel at following complex instructions, editing images and maintaining concept consistency. However, they are still evaluated by disjoint toolkits:…

Omni-modal models that have multimodal input and output are emerging. However, benchmarking their multimodal generation, especially in image generation, is challenging due to the subtleties of human preferences and model biases. Many image…

Generative artificial intelligence (GenAI) text-to-image systems are increasingly used to generate architectural imagery, yet their capacity to reproduce accurate images in a historically rule-bound field remains poorly characterized. We…

Safety filters in commercial text-to-image (T2I) models systematically block legitimate artistic content involving the human figure, treating classical nude photography with the same restrictiveness as explicit material. While prior…

With generative models becoming increasingly sophisticated and diverse, detecting AI-generated images has become increasingly challenging. While existing AI-genereted Image detectors achieve promising performance on in-distribution…

As agentic coding systems decompose work across multiple model instances, a critical safety question is whether those instances can coordinate to achieve a hidden malicious objective while remaining aligned with user intent. We introduce…

Personalized image generative models are highly proficient at synthesizing images from text or a single image, yet they lack explicit control for composing objects from specific parts of multiple source images without user specified masks…

The ability of Large Language Models (LLMs) to generate structured outputs, such as JSON, is crucial for their use in Compound AI Systems. However, evaluating and improving this capability remains challenging. In this work, we introduce…

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications…

Recent advances in video generation have enabled high-fidelity video synthesis from user provided prompts. However, existing models and benchmarks fail to capture the complexity and requirements of professional video generation. Towards…

This paper benchmarks eight multi-modal large language models from three families (GPT-5, Gemini 2.5, and open-source Gemma 3) on three diverse openly available invoice document datasets using zero-shot prompting. We compare two processing…

A critical need has emerged for generative AI: attribution methods. That is, solutions that can identify the model originating AI-generated content. This feature, generally relevant in multimodal applications, is especially sensitive in…

As LLMs advance their reasoning capabilities about the physical world, the absence of rigorous benchmarks for evaluating their ability to generate scientifically valid physical models has become a critical gap. Computational mechanics,…

How reliably can structured intent representations preserve user goals across different AI models, languages, and prompting frameworks? Prior work showed that PPS (Prompt Protocol Specification), a 5W3H-based structured intent framework,…

Designing a computational imaging system -- selecting operators, setting parameters, validating consistency -- requires weeks of specialist effort per modality, creating an expertise bottleneck that excludes the broader scientific community…

Environment designers in the entertainment industry create imaginative 2D and 3D scenes for games, films, and television, requiring both fine-grained control of specific details and consistent global coherence. Designers have increasingly…

This research investigates the use of customized GPT models to enhance prompting proficiency among architecture students when generating AI-driven images. Prompt engineering is increasingly essential in architectural education due to the…

Current AI safety relies on behavioral monitoring and post-training alignment, yet empirical measurement shows these approaches produce no detectable pre-commitment signal in a majority of instruction-tuned models tested. We present an…

Deep generative models have achieved promising results in image generation, and various generative model hubs, e.g., Hugging Face and Civitai, have been developed that enable model developers to upload models and users to download models.…

How do multimodal models solve visual spatial tasks -- through genuine planning, or through brute-force search in token space? We introduce \textsc{MazeBench}, a benchmark of 110 procedurally generated maze images across nine controlled…