Guaranteed Optimal Compositional Explanations for Neurons 事件

Guaranteed Optimal Compositional Explanations for Neurons arXiv:2511.20934v2 Announce Type: replace-cross Abstract: Compositional explanations are a family of methods that aim to describe the spatial alignment between neurons' receptive field activations and concepts through logical rules, typically computed via a search over all possible concept combinations. Since computing the spatial alignment over the entire state space is computationally infeasible, the literature commonly adopts assumpti