18 citations · 25 across the 7 of their papers we have counts for
9 papers
Is a Linear Probe Evidence of a Linear Representation?
Nadir Kutluozen, Christian Internò, David Klindt
The linear representation hypothesis holds that pretrained vision models encode generative factors as linearly decodable directions in feature space, and comes with a standard meth…
GeoPrior-Mamba: Structured Process Priors with Mamba for Fine-Resolution XCO2 Reconstruction
Zhao Meng, Yinan Cai, Siru Zhong +2
Reconstructing fine-resolution column-averaged dry-air CO2 (XCO2) fields from sparse satellite observations requires models to infer spatial structure that is only weakly constrain…
MotionJEPA: Preventing Temporal Feature Collapse by Capturing Visual Changes in Latent Space
Markus Karmann, Shile Li, Christian Internò +10
Joint Embedding Predictive Architectures (JEPAs) are a promising paradigm for learning task-agnostic latent world models without visual reconstruction. However, standard JEPA train…
GEOPHYS: The Geometry of Physical Plausibility
Christian Internò, Alexander Pondaven, Habon Issa +8
While humans can identify physically implausible events within milliseconds, machine learning approaches addressing the same problem are extremely slow and expensive. They either r…
When Does LeJEPA Learn a World Model?
David Klindt, Yann LeCun, Randall Balestriero
A representation that scrambles the true degrees of freedom of the world cannot support reliable planning or compositional generalization. We prove that LeJEPA (alignment plus Gaus…
Similarity of Neural Network Representations in Superposition
Sunny Liu, Habon Issa, André Longon +4
Comparing internal representations is a central goal in neuroscience and machine learning, but standard linear alignment metrics (Representational Similarity Analysis, Centered Ker…
Understanding Neural Coding on Latent Manifolds by Sharing Features and Dividing Ensembles
Martin Bjerke, Lukas Schott, Kristopher T. Jensen +3
Systems neuroscience relies on two complementary views of neural data, characterized by single neuron tuning curves and analysis of population activity. These two perspectives comb…
Score-Based Generative Classifiers
Roland S. Zimmermann, Lukas Schott, Yang Song +2
The tremendous success of generative models in recent years raises the question whether they can also be used to perform classification. Generative models have been used as adversa…
Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding
David Klindt, Lukas Schott, Yash Sharma +4
We construct an unsupervised learning model that achieves nonlinear disentanglement of underlying factors of variation in naturalistic videos. Previous work suggests that represent…