Sihui Wei — accepted AI-conference papers

2026

Deep neural networks divide and conquer dihedral multiplication

Sihui Wei, Gavin McCracken, Gabriela Moisescu-Pareja, Harley Wiltzer, Doina Precup, Irina Rish +1

ICML 2026poster

We find multilayer perceptrons and transformers both universally learn an instantiation of the same divide-and-conquer algorithm that requires only a logarithmic number of neural representations to solve dihedral multiplication. Clustering neurons based on similar activation behaviour reveals remark…

Cited by 0 Source ↗Scholar ↗

2025

Where Did That Come From? Sentence-Level Error-Tolerant Attribution

Ori Ernst, Aviv Slobodkin, Meng Cao, Sihui Wei, Jackie CK Cheung

EMNLP 2025

Attribution is the process of identifying which parts of the source support a generated output. While attribution can help users verify content and assess faithfulness, existing task definitions typically exclude unsupported or hallucinated content leaving them unattributed, overlooking the potentia

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗