3 papers
cs.CV2026
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…
cs.AI2026
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…
math.ST2026
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…