PhysisForcing, a new training framework from Peking University and NVIDIA, lifts robot manipulation success from 16 to 24 percent by injecting physics supervision into video diffusion models at ...

I believe many people have tried the image generation AI "Stable Diffusion" at least once.The same mechanism——Diffusion Model ...

Google's latest breakthrough, Gemini Robotics, is pushing the boundaries of AI-driven automation. By integrating advanced large language models (LLMs) into robotics, Gemini enables machines to ...

One of the most stubborn problems in artificial intelligence is teaching an agent to carry out tasks that stretch far into ...

September 25, 2026OverviewIn this episode of Latent Space, a technical podcast for AI engineers, we welcome Anastasis, ...

Diffusion models gradually refine and produce a requested output, sometimes starting from random noise—values generated by the model itself—and sometimes working from user-provided data. Think of ...

Black Forest Labs (BFL) launched FLUX 3 on July 23, 2026, and it is not an image model with video bolted on. The Freiburg, Germany-based company — whose founding team built the latent diffusion ...

It’s hard to ignore the buzz around artificial intelligence these days. Whether it’s the promise of smarter virtual assistants, robots that can perform backflips, or AI models that churn out lifelike ...

Robots are already being used in a growing range of industries, including dining, health care, and construction. While they previously relied on rule-based, reactive systems, the emergence of world ...