Apple has released a public demo of the 4M AI model it developed in collaboration with the Swiss Federal Institute of Technology Lausanne (EPFL). The technology debuts seven months after the model was first open-sourced, allowing informed observers the opportunity to interact with it and assess its capabilities. Apple says 4M was built by applying masked modeling to a single unified Transformer encoder-decoder “across a wide range of input/output modalities — including text, images, geometric and semantic modalities, as well as neural network feature maps.” Continue reading Apple Launches Public Demo of Its Multimodal 4M AI Model

The first Saturday morning session of SMPTE’s Technology Summit On Cinema at NAB focused on factors that could impact the UHD TV rollout, including research on what humans are able to see and observe. During a panel titled “Understanding the Human Vision System,” Dr. Jenny Read of Newcastle University Institute of Neuroscience set the stage by discussing four parameters of vision: spatial resolution, temporal resolution, dynamic range, and color perception. Related studies from Dolby, EBU and EPFL were presented. Continue reading SMPTE Tech Summit: Understanding the Human Vision System