V-JEPA

Yann LeCun, chief AI scientist at Meta, launched the JEPA (Joint Embedding Predictive Architectures) model architecture in 2022. The following year, he developed an "I-JEPA" image prediction model based on the JEPA architecture. He has now launched a video prediction model called "V-JEPA". It is reported that the relevant JEPA architecture and I-JEPA/V-JPA models focus on "prediction ability", claiming to be able to "understand human...