arXiv:2409. 10094v3 Announce Type: replace-cross Abstract: Out-of-Distribution (OoD) detection aims to justify whether a given sample is from the training distribution of the classifier-under-protection, i.
By Kun Fang, Zuopeng Yang, Haibo Hu, Xiaolin Huang, Jie Yang, Qinghua Tao
arXiv:2607. 07671v1 Announce Type: new Abstract: Probabilistic circuits (PCs) can model complex joint distributions while supporting exact and efficient computation of many inference queries.
By Adrian Ciotinga, Yeming Dai, YooJung Choi
arXiv:2609.23892v1 Announce Type: new
Abstract: Mechanistic interpretability defines features as the fundamental units of a neural network and circuits as the weighted subgraphs that carry out its co...
By Edward G. Friedman, Xiangchen Song
The paper introduces MACCHIATO, a training algorithm that builds a ReLU‑MLP from partial truth‑table data while simultaneously constructing an explicit Boolean circuit over AND, OR, and XOR gates that certifies the network’s computation. The method iteratively projects residuals onto low‑dimensional Boolean classes, compiles the resulting circuit into a ReLU‑MLP, and uses logic minimization and influence‑based variable selection to achieve a six‑layer network with provable truth‑table error bounds. Experiments on synthetic random‑junta tasks show that these certified networks outperform Adam‑trained MLPs in data‑sparse or projection‑aligned regimes and complete faster than flat ESPRESSO in certain settings.
By Hrad Ghoukasian, Anastasis Kratsios
arXiv:2606. 23872v1 Announce Type: cross Abstract: As generative models increasingly produce samples that are indistinguishable from human-created content, it becomes difficult to determine whether a given data point was part of a model's natural training set or was generated by the model itself, especially when models memorize and reproduce training data.
By Bihe Zhao, Michel Meintz, Juangui Xu, Franziska Boenisch, Adam Dziedzic
The paper introduces Concept-Targeted Attribution (CTA), a method that trains attribution graphs to explain the emergence of internal concept representations in language models, rather than just the final token prediction. CTA produces probe-specific circuits that reveal which internal computations drive a linear probe’s accuracy, and cross-layer transcoders demonstrate that these graphs contain predictive structure across multiple concept categories. Causal ablations show that probe-targeted and logit-targeted graphs capture distinct mechanisms, with probe-relevant features affecting internal concept scores and logit-relevant features altering generated tokens.
By Vedant Palit, Florent Draye, Terry Jingchen Zhang, Bernhard Sch\"olkopf, Zhijing Jin