LATENT enables the simulation of highly-dynamic tennis rallies by human athletes, showcasing versatile skills in a competitive environment. Developed by researchers from Tsinghua University, Peking University, and other institutions, it utilizes advanced AI techniques for real-time performance.

LoGeR enables dense 3D reconstruction of extremely long videos by processing them in chunks with a hybrid memory module, addressing quadratic complexity issues. It utilizes Sliding Window Attention for local alignment and Test-Time Training to maintain global consistency, effectively reducing drift over sequences of up to 19,000 frames.

Antscan is a new 3D atlas that provides detailed micrometer-resolution reconstructions of ant anatomy. The platform was developed by a multidisciplinary team including entomologists, physicists, computer scientists, and imaging specialists.

AI models are now capable of generating highly convincing human-like images, making it challenging for most people to detect AI-generated faces. Even trained "super recognizers" show only marginal improvements in identifying these images, as traditional visual clues are becoming increasingly elusive.