New experimental AI tool helps people explore the context and origin of images seen online.
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.
The paper introduces the CO-AID dataset, which captures systematic defects in state‑of‑the‑art text‑to‑image models when prompts involve complex composition such as multiple entities and attributes. Researchers manually curated 651 reference images across people, hand, object, and scene categories, edited ChatGPT‑generated prompts to emphasize compositional factors, and generated AI images with three T2I models. A subjective study with 29 participants produced multi‑label defect annotations, enabling training of a deep model that predicts defects and improves image generation.
Our new paper analyzes the important ways AI systems organize the visual world differently from humans.
arXiv:2408. 00001v2 Announce Type: replace-cross Abstract: Visual diffusion models have revolutionized the field of creative AI, producing high-quality and diverse content.
arXiv:2606. 28510v1 Announce Type: cross Abstract: Across social and online platforms, people are increasingly exposed to AI-generated images.
OpenAI advances AI content provenance with Content Credentials, SynthID, and a verification tool to help people identify and trust AI-generated media.
arXiv:2504. 06138v3 Announce Type: replace-cross Abstract: Professional users need tools to help them gain actionable insights from large multimedia collections.
“SceneSmith” system uses collaborative AI agents to create realistic 3D environments of places like kitchens, hotels, and living rooms, where robots can simulate everyday chores.
arXiv:2606. 14748v1 Announce Type: cross Abstract: We present the Membership Inference Test (MINT) Demo 2, a framework designed to improve transparency in machine learning training processes.
The paper explores whether CLIP embeddings can detect AI-generated images by using a frozen CLIP model to extract visual embeddings and training lightweight classifiers on top. On the CIFAKE benchmark, the approach achieves 95% accuracy without language reasoning, and 85% accuracy after few-shot adaptation with 20% of the data. Certain image types, such as wide-angle photographs and oil paintings, remain challenging, highlighting unexplored difficulties in AI-generated image classification.
Towards Data Science has released a video showcase titled "Introducing ShipAI," which highlights real‑world AI work. The post announces this new visual resource and its focus on practical AI applications. It is positioned as a first look into the platform’s capabilities.
