Tag: Self-Supervised Learning
Google’s SensorFM: A Foundation Model for Wearable Health Data
Google Research introduces SensorFM, a foundation model trained on a trillion minutes of wearable sensor data from 5 million people to predict health outcomes.
LeWorldModel: Yann LeCun’s End-to-End JEPA Breakthrough
Yann LeCun introduces LeWorldModel (LeWM), the first end-to-end JEPA trained from raw pixels, solving the collapse problem in world models.