# From Pixels to Predictive Codes: What V-JEPA 2 Means for Embodied-Simulation Research

A technical reading of predictive video representations and their relevance to embodied simulation.

Date: June 24, 2025
Type: Technical note
Status: Technical note
Credit: Author
Authors: Richard Everts

## Predicting useful structure

This note examines V-JEPA 2 through the lens of embodied simulation. It focuses on the distinction between predicting compressed representations and reconstructing every detail of an image.

Richard considers how prediction-first systems might relate to SIML's research questions. The piece is a reading of public research and a discussion of possible connections, rather than a claim to have developed V-JEPA 2.

## From reading to experiment

The later SIML FEPGate benchmark explores one concrete connection with a latent planner. Keeping the two records separate makes the progression clear: interpretation and proposed bridges first, then a reported implementation and comparison.

The original note contains the technical discussion and links for further reading.

## Sources
- [Original technical note](https://www.siml.life/notes/From-Pixels-to-Predictive-Codes-What-V-JEPA-2-Means-for-Embodied-Simulation-Research)