Top Tweets for #LeWorldModel
about Generative AI vs JEPA (Joint-Embedding Predictive Architecture)
#LeWorldModel #LeWM
https://t.co/OVtYlHqRSo
Yann LeCun was right the entire time. And generative AI might be a dead end.
For the last three years, the entire industry has been obsessed with building bigger LLMs. Trillions of parameters. Billions in compute.
The theory was simple: if you make the model big enough, it will eventually understand how the world works.
Yann LeCun said that was stupid.
He argued that generative AI is fundamentally inefficient.
When an AI predicts the next word, or generates the next pixel, it wastes massive amounts of compute on surface-level details.
It memorizes patterns instead of learning the actual physics of reality.
He proposed a different path: JEPA (Joint-Embedding Predictive Architecture).
Instead of forcing the AI to paint the world pixel by pixel, JEPA forces it to predict abstract concepts. It predicts what happens next in a compressed "thought space."
But for years, JEPA had a fatal flaw.
It suffered from "representation collapse."
Because the AI was allowed to simplify reality, it would cheat. It would simplify everything so much that a dog, a car, and a human all looked identical.
It learned nothing.
To fix it, engineers had to use insanely complex hacks, frozen encoders, and massive compute overheads.
Until today.
Researchers just dropped a paper called "LeWorldModel" (LeWM).
They completely solved the collapse problem.
They replaced the complex engineering hacks with a single, elegant mathematical regularizer.
It forces the AI's internal "thoughts" into a perfect Gaussian distribution.
The AI can no longer cheat. It is forced to understand the physical structure of reality to make its predictions.
The results completely rewrite the economics of AI.
LeWM didn't need a massive, centralized supercomputer.
It has just 15 million parameters.
It trains on a single, standard GPU in a few hours.
Yet it plans 48x faster than massive foundation world models. It intrinsically understands physics. It instantly detects impossible events.
We spent billions trying to force massive server farms to memorize the internet.
Now, a tiny model running locally on a single graphics card is actually learning how the real world works.

15 millions de paramètres. 1 seul GPU.
#LeWorldModel de @YLeCun est un 1er pas vers les world models capable de comprendre le monde physique
Les premiers tests sont très encourageants !
https://t.co/oUWYtxvERb
https://t.co/L2BVLugYAT
#LeWorldModel @amilabs @ylecun
#ZadienLabs #SovereignOrderOfEnigmaticRepublics
@xai @elonmusk @neuralink @uspto
#LeWorldModel is interesting for one reason: it removes the hardest part of building world models, the collapse.
And once that problem is gone, a few things follow:
– physics modeling becomes lightweight & open
– Simulation no longer needs massive computing
– more people can build “world-aware” systems
When the base layer becomes accessible, the bottleneck shifts. Not to compute, but to what you build with it.🕹
#MetaOne #M1 #AI #Gaming
Just read LeCun's latest paper. His team trained the first world model that can't collapse.
Let me explain why this matters.
It's called LeWorldModel.
World models predict what happens next physically. Objects moving, falling, colliding.
That's the base layer for robots that plan, cars that simulate before they steer, any AI that acts in reality instead of just talking about it.
The catch is nobody could train these reliably.
The models kept cheating. They'd map every input to the same output. Like a weather app stuck on "sunny" forever. Technically predicting. Completely useless.
So teams piled on fixes. Frozen encoders, stop-gradient hacks, 6+ loss hyperparameters. A fragile stack too brittle for production.
This team asked a different question. What if you make collapse mathematically impossible?
An encoder turns each video frame into a small vector. A predictor takes that vector plus an action and guesses the next one.
First loss: how wrong was the guess.
Second loss: a regularizer called SIGReg that checks if vectors spread out like a bell curve. If they start looking the same, the loss spikes.
The model can't cheat because the math won't let it.
That simplicity is what makes the results possible.
Six hyperparameters became one. 15M parameters. Trains on one GPU in hours. Plans 48x faster. Encodes with ~200x fewer tokens.
Open-source. I could run this on my own hardware.
Which changes who gets to build physical AI. Not just big labs anymore. Any team, any startup, any grad student.
LeCun has pushed JEPA as the path forward. The criticism was always training instability. This paper removes that objection.
Two directions compete in AI right now. Bigger LLMs with more compute. Or small models learning physics from raw pixels.

#Tech24H A research team led by Turing Award winner #YannLeCun recently released #LeWorldModel (#LeWM), a new lightweight world model. It fundamentally addresses issues common in traditional #JEPA models, such as training instability, collapse, excessive hyperparameters, and high computational costs. It is the first world model capable of stable end-to-end training directly from raw pixels. The model consists of just two core components, two loss terms, and 15 million parameters, requiring only a few hours of training on a single GPU, with only one effective tunable hyperparameter. In addition, LeWM achieves a qualitative leap in planning speed, reaching up to 48 times that of traditional large model methods, with a single planning session taking less than one second.
https://t.co/NKqI2DIytM

Last Seen Hashtags on Sotwe
Most Popular Users

Elon Musk 
@elonmusk
240.3M followers

Barack Obama 
@barackobama
119.3M followers

Donald J. Trump 
@realdonaldtrump
111.6M followers

Cristiano Ronaldo 
@cristiano
109.5M followers

Narendra Modi 
@narendramodi
107M followers

Rihanna 
@rihanna
97.4M followers

NASA 
@nasa
92.1M followers

Justin Bieber 
@justinbieber
90.7M followers

KATY PERRY 
@katyperry
87.1M followers

Taylor Swift 
@taylorswift13
80.9M followers

Lady Gaga 
@ladygaga
72.5M followers

Kim Kardashian 
@kimkardashian
69.5M followers

Virat Kohli 
@imvkohli
69M followers

YouTube 
@youtube
68.6M followers

Bill Gates 
@billgates
63.6M followers

The Ellen Show
@theellenshow
62.5M followers

CNN 
@cnn
61.9M followers

Neymar Jr 
@neymarjr
61.7M followers

X 
@x
60.9M followers

Selena Gomez 
@selenagomez
60.2M followers






