Paper traces Granger tests toward causal structure in dynamical models
The review says Granger tests detect predictive links among signals, not causal links among generating mechanisms.
Stories per day · 30 days
Relatedcausal-inference1diffusion1dynamical-systems1granger-causality1image-generation1language-conditioning1model-predictive-control1robotics1vae1visual-tokenizer1world-models1
5 stories, newest first · one card per story
Stories tagged #latent-models
LaLa-World scales latent world models with language actions
The paper reports comparable planning to an RAEv2 video baseline at 6 times less training cost.
RoAR-VAE improves latent diffusability via robust prediction
It beats the strongest baseline tokenizer by 2.19 points and FLUX.1-VAE small-text accuracy by 16.93 points.
RoboJEPA: Scaling Robotic Latent World Models
RoboJEPA, an 8B JEPA world model on 12 embodiments, reports compute scaling laws for robotic planning.
Time series generation with spectrally aligned latent flow matching
Spectrally aligned latent flow matching generates time series that preserve Fourier, wavelet, and signature structure.