With the rise of large-scale foundation models, efficiently adapting them to downstream tasks remains a central challenge. Linear probing, which freezes the backbone and trains a lightweight head, is ...

With the rise of large-scale foundation models, efficiently adapting them to downstream tasks remains a central challenge. Linear probing, which freezes the backbone and trains a lightweight head, is ...

#2 in a series on cognitive science and AI

Aligning foundation models with human judgments enables them to more accurately approximate human behaviour and uncertainty across various levels of visual abstraction, while additionally improving th...

Aligning AI vision models with human knowledge, improves their robustness and ability to generalize.

New research forms a bridge between human and machine representation

Biological and artificial information processing systems form representations of the world that they can use to categorize, reason, plan, navigate, and make decisions. How can we measure the...

The Platonic Representation Hypothesis claims that recent foundation models are converging to a shared representation space as a function of their downstream task performance, irrespective of the...

An interpretability framework that compares how humans and deep neural networks process images has been presented. Their findings reveal that, unlike humans, deep neural networks focus more on visual ...

The Platonic Representation Hypothesis claims that recent foundation models are converging to a shared representation space as a function of their downstream task performance, irrespective of the obje...

Lukas Muttenthaler (Google DeepMind, TU Berlin)

CBS CoCoNUT: A new interest group that comes together every two weeks to have an informal exchange about cognitive computational neuroscience.

The Platonic Representation Hypothesis claims that recent foundation models are converging to a shared representation space as a function of their downstream task performance, irrespective of the obje...

If you wish to show your support for the letter below regarding apparent inaction by the Royal Society in the face of breaches of its code of conduct by Elon Musk FRS, please sign below. I invite anyo...

On mental health, psychedelics and life This is a story about mental health, psychedelics, psychology and the mind. It is a story about the joy of family, the joy of friends, the joy of being in love...

The ability of language models to learn a task from a few examples in context has generated substantial interest. Here, we provide a perspective that situates this type of supervised few-shot learning...

Biological and artificial information processing systems form representations of the world that they can use to categorize, reason, plan, navigate, and make decisions. How can we measure the similarit...

Deep neural networks have achieved success across a wide range of applications, including as models of human behavior in vision tasks. However, neural network training and human learning differ in...