The problem is challenging as it requires not only the reconstruction of visible parts but also the hallucination of invisible regions. Consequently, this problem is often ill-posed and corresponds to multiple plausible solutions because of insufficient evidence from a single image.

These works assume an arbitrary neural network with no prior knowledge of decoding algorithms, and accordingly, face the challenge of learning a decoding algorithm.

We present ClimSim, the largest-ever dataset designed for hybrid ML-physics research.

The capability of generalizing to out-of-distribution data is crucial for the deployment of machine learning models in the real world.

Our environment is riddled with sensory stimuli that are noisy, ambiguous, and often incomplete, necessitating organisms to handle uncertainty in their sensory observations.

Here we test whether these scaling "laws" hold for the task of modeling the human brain.