AutoSlim uses a Random Forest model trained on prior execution features to prune redundant parts of automata graphs, reducing FPGA resources by up to 40% in symbolic accelerators with a verification check for equivalence.
Anmlzoo: a benchmark suite for exploring bottlenecks in automata processing engines and architectures
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Machine Learning-Based Graph Simplification for Symbolic Accelerators
AutoSlim uses a Random Forest model trained on prior execution features to prune redundant parts of automata graphs, reducing FPGA resources by up to 40% in symbolic accelerators with a verification check for equivalence.