Joint Embedding Predictive Architecture

Created
Created
2025 Mar 23 21:8
Editor
Creator
Creator
Seonglae Cho
Edited
Edited
2025 Mar 23 21:13

JEPA

A network architecture that encodes input data (x) and its corresponding target data (y) into embedding vectors (sₓ, sᵧ), then predicts y's embedding based on x's embedding
  1. Sensory Module extracts environmental states from input data into internal representations
  1. World Module predicts future states from sensory representations and incorporates latent variables to manage uncertainty
  1. Cost Module calculates the cost of predicted states using intrinsic costs and a learnable critic
  1. Actor Module searches for action sequences that minimize cost and decides on actual actions
Joint Embedding Predictive Architectures
 
 
 
 
 

Recommendations