arXiv AI By Zihao Qi, Christopher Earls

Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders

Read the original on arXiv AI →

arXiv:2607. 01336v1 Announce Type: cross Abstract: Neural Quantum States (NQS) are a remarkably expressive class of variational ans\"atze for quantum many-body wavefunctions, yet little is understood about their internal mechanisms: trained on variational objectives alone, how do NQS accurately capture physical observables that they have never been explicitly optimized for?

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jul 2

When AI meets quantum information: A comprehensive review

arXiv:2607. 00365v1 Announce Type: cross Abstract: Artificial intelligence (AI) and quantum information (QI) are rapidly co-evolving.

By Min Chen, Yu Gan, Xin Jin, Yuqing Li, Junqi Wang, Zeguan Wu, Yunfei Wang, Bingzhi Zhang, Priyam Srivastava, Tianlong Chen, Ankit Kulshrestha, Yuan Liu, Juan Jos\'e Mendoza-Arenas, Kaushik P. Seshadreesan, Sarvagya Upadhyay, Xueyue Zhang, Quntao Zhuang, Junyu Liu
arXiv Machine Learning
Jul 27

Explainable quantum-compressed machine learning for complex fluid flows

arXiv:2607. 21688v1 Announce Type: cross Abstract: Machine-learning surrogates of physical systems face a paradox: explainable models facing the challenge of expressivity to capture complex nonlinear flows, whereas expressive deep surrogates match high-fidelity simulations only through massive parameterisations that turn the learned dynamics into a black box.

By Xiao Xue, Maida Wang, Mingyang Gao, Minh Chung, Peter V. Coveney