5 papers
A Phenomenology of Neural Geometry in Vision-Language-Action Models
Mozes Jacobs, Aiden Swann, Mathilde Papillon +16
Robotic manipulation is inherently geometric, but what shape does the world take inside the policy that performs it? Prior work on vision-language-action (VLA) policies establishes…
Causal Analysis of Robot Foundation Models Enables Efficiency Gains
Aiden Swann, Mathilde Papillon, Mozes Jacobs +13
Vision-language-action (VLA) models are a promising approach to general purpose robot manipulation. While the internal computation of vision-language models, which compose the back…
Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds
Thomas Fel, Matthew Kowal, Mozes Jacobs +22
What is the geometry of a visual percept? The most widely used protocols for decomposing neural network representations into interpretable parts treat concepts as isolated directio…
Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction
Li Puyin, Jiyuan Tan, Ahmad Jabbar +2
We present a method for diagnosing interpretation in neural networks by identifying an input subspace where a proposed interpretation is highly faithful. Our method is particularly…
Counterfactual Spaces
Junhyung Park, Fanny Yang, Thomas Icard
We mathematically axiomatise the stochastics of counterfactuals, by introducing two related frameworks, called counterfactual probability spaces and counterfactual causal spaces, w…