2 papers
cs.LG2026
Extraction meets Distillation - cryptanalytic techniques to recover parameters from a Deep Neural Network
Biprarshi Biswas, Arya Anshuman Ojha, Yubaraj Das +5
We study fully connected neural-network reconstruction by combining cryptanalytic weight-direction extraction with learning from predicted labels. We adapt a ReLU extraction implem…
cond-mat.str-el2025
Pressure tuning of Kitaev spin liquid candidate NaCoSbO
E. H. T. Poldi, R. Tartaglia, G. Fabbris +17
The search for Kitaev's quantum spin liquid (KQSL) state in real materials has recently expanded with the prediction that honeycomb lattices of divalent, high-spin cobalt ions coul…