Exactly. I've been arguing for dynamical world models (for planning) since at least 2016 (e.g. in my NIPS 2016 keynote) and doing so using JEPA since 2021/2022 (before ChatGPT), e.g. in this 2022 paper: https://
openreview.net/forum?id=BZ5a1
r-kVsf
…
This has nothing to do with Llama4.
@ylecun
-
Dynamical World Models and JEPA for AI Planning Since 2016
By
–
-
Meta-FAIR Releases Open Source AI Model
By
–
Open source AI FTW.
— Yann LeCun (@ylecun) 18 avril 2025
From Meta-FAIR. https://t.co/D9PrGYzeeoOpen source AI FTW.
From Meta-FAIR. -
World Models Revolutionizing Autonomous Driving Technology
By
–
World models in autonomous driving FTW !
-
Defining Openness in Machine Learning Systems: Fine Details
By
–
In case you care about the fine details of what "open" means in the context of ML systems. https://
arxiv.org/abs/2405.15802 -
Language Supervision Unnecessary for Multimodal Visual Representations
By
–
New paper from FAIR+NYU:
Q: Is language supervision required to learn effective visual representations for multimodal tasks? A: No. -
Be a non-hallucinating human in the LLM world
By
–
In the X world of bots and LLMs, be a non-hallucinating human.
-
France Strengthens Support for Science and Scientists
By
–
France standing up for science (and scientists).
