4 papers
On the Depth Scalability of Logic Gate Networks
Taegun An, Dohun kim, Haebeom Lee +1
Logic Gate Networks (LGNs) compute through compositions of Boolean operations, yet existing LGNs do not reliably benefit from increased depth. We identify two causes: optimization…
SCOPE: Entanglement Frontier Escape for Source-Free Class Unlearning
Junhao Cai, Dohun Kim, Sung Il Choi +4
Source-free class unlearning erases whole classes using only the forget data, judged at the representation level, where features can leak a class the head no longer predicts. Exist…
Retain-Neutral Surrogates for Min-Max Unlearning
Junhao Cai, Dohun Kim, Dowon Kim +4
Machine unlearning seeks to remove the influence of designated training data while preserving performance on the remaining data. Approximate unlearning can be viewed as a local edi…
Improving the Fidelity of CNOT Circuits on NISQ Hardware
Dohun Kim, Minyoung Kim, Sarah Meng Li +1
We introduce an improved CNOT synthesis algorithm that considers nearest-neighbour interactions and CNOT gate error rates in noisy intermediate-scale quantum (NISQ) hardware. Compa…