Researchers at DeepMind have developed a new AI system called D4RT that can reconstruct and track objects in four dimensions. This means it can analyze data from various points in time, such as video frames, and understand the relationships between them. According to the developers, D4RT is up to 300 times faster than previous methods for this task. The system uses a unified approach to combine reconstruction and tracking, making it more efficient. --- Why it matters: This matters because it enables AI systems to better understand dynamic environments and track objects over time, which could improve applications such as autonomous vehicles, surveillance systems, and video analysis tools. Source: https://deepmind.google/blog/d4rt-teaching-ai-to-see-the-world-in-four-dimensions/