4 papers
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…
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…
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…
HCF: Hierarchical Cascade Framework for Distributed Multi-Stage Image Compression
Junhao Cai, Taegun An, Chengjun Jin +3
Distributed multi-stage image compression -- where visual content traverses multiple processing nodes under varying quality requirements -- poses challenges. Progressive methods en…