2 papers
cs.LO2025
Just-In-Time Piecewise-Linear Semantics for ReLU-type Networks
Hongyi Duan, Haoyang Liu, Jian'an Zhang +2
We present a JIT PL semantics for ReLU-type networks that compiles models into a guarded CPWL transducer with shared guards. The system adds hyperplanes only when operands are affi…
cs.LG2025
Rethinking Selectivity in State Space Models: A Minimal Predictive Sufficiency Approach
Yiyi Wang, Jian'an Zhang, Hongyi Duan +2
State Space Models (SSMs), particularly recent selective variants like Mamba, have emerged as a leading architecture for sequence modeling, challenging the dominance of Transformer…