SCS researchers, including CSD's Guying Lin (shown), have developed a new scene-generation framework that creates physically realistic, simulation-ready 3D scenes from text prompts. PAT3D generates 3D ...

Microsoft's AI image generator offers impressive realism and text rendering, but strict content limits and 1:1-only output hold it back.

Canva unveiled an AI tool called Magic Layers that uses an AI to transform an ordinary image into editable layers. Do you see ...

Midjourney 8 adds in-image text, HD mode, and personalization profiles, but long captions still render with occasional errors.

Memories.ai is building a large visual memory model that can index and retrieve video-recorded memories for physical AI.

A new font-rendering attack causes AI assistants to miss malicious commands shown on webpages by hiding them in seemingly harmless HTML.

Might just be my new favorite thing about Claude.

Political Director and Executive Director of Politics and White House, CBS News Fin Daniel Gómez is CBS News' political director and executive director, Politics and White House. In this role, Gómez ...

All three editors successfully generated and extended a multi-page static website from identical natural-language prompts. Cursor emphasized production-oriented polish and executed large redesigns and ...

Alternative text (“alt text”) is the text description of an image that screen readers and other assistive technologies use to assist people with different visual abilities. Alt text is also displayed ...

According to @AIatMeta, Meta has launched SAM Audio, the first unified AI model capable of isolating individual sounds from complex audio mixtures using diverse prompts, including text, visual cues, ...

Every year, designers at Pew Research Center create hundreds of charts, maps and other data visualizations. We also help make a range of other digital products, from “scrollytelling” features to ...