AI’s attribution problem gets worse as models scale

MIT researchers found that as diffusion models scale, individual training examples have less measurable influence on outputs, ...
TechCrunch

Stability AI releases a new audio model that can create 6-minute songs

Stability AI, the company behind Stable Diffusion, is releasing a new family of audio models, called Stability Audio 3.0. The top model can generate professional-grade music of more than six minutes ...
Tech Times on MSN

FLUX 3 launches: Black Forest Labs enters video, audio, and physical AI in one model

FLUX 3, Black Forest Labs' new multimodal AI model, generates video with native synchronized audio and drives factory robots at Audi from a single shared architecture — beating Runway Gen-4.5 in 77% ...
Phys.org

Q&A: What AI actually does in diffusion models for drug design

In the search for new drugs, artificial intelligence in the form of diffusion models is being used in drug design. What exactly does AI do in this context? Dr. Andrea Mastropietro and Prof. Dr. Jürgen ...
Forbes

Why AI Models Break Outside The Lab

This voice experience is generated by AI. Learn more. This voice experience is generated by AI. Learn more. AI video systems usually perform well in controlled demonstrations. Clean data, stable ...