ARDY is an autoregressive diffusion model designed for interactive motion generation, supporting online text prompting and flexible long-horizon kinematic constraints (root paths/waypoints, full-body ...

Open-source world model AlayaWorld, released by China’s Shanda AI Research in July 2026, sustains interactive video ...

Creative work already trained the AI models replacing its makers. Judges now disagree on whether that counts as theft or fair ...

When you’re looking at tennis as a game, it’s a player for two to five hours on their own,” points out author Sunita Kumar Nair, whose new book Ace: The Times & Style of Tennis, explores how fashion ...

Google DeepMind released DiffusionGemma on June 10, 2026, an experimental open-weights model that writes text using discrete diffusion rather than the token-by-token method behind GPT-style systems, ...

Google's open-source diffusion language model generates 256 tokens in parallel and self-corrects, hitting 4x speed on one GPU at a cost to quality.

Martin Scorsese is the latest Oscar-winning director to hop on the AI wagon, joining the AI firm Black Forest Labs as an adviser in a bid to “push the bounds of creativity to create deeper and richer ...

Over 15 billion AI images have been generated since 2022. Whether you want the best AI art generator for stylized creative work, a best free text to image AI for quick marketing assets, or one of the ...

Black Forest Labs has long punched above its weight in the AI image generation space. Its next move? Powering physical AI. Standing inside the HumanX conference in San Francisco’s Moscone Center, it’s ...

Abstract: Remote sensing image classification refers to the task that using algorithms to categorize satellite or aerial imagery into different land cover types. In the real world, long-tailed data ...

Z.ai announced their image generation model, GLM-Image, on January 14, 2026 (local time). It is a hybrid model that combines an autoregressive model and a diffusion model. The autoregressive model is ...