Research map / Learning theory and algorithms / Combinatorial and search optimization
Neural Circuit Synthesis from Specification Patterns
Frederik Schmitt, Christopher Hahn, Markus Norman Rabe, Bernd Finkbeiner
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| increase beam size from 1 to 16 | Hierarchical Transformer · Testset | semantic accuracy: 53.1 -> 78.7 | Improved |
| increase beam size from 1 to 16 | Hierarchical Transformer · SYNTCOMP | semantic accuracy: 51.7 -> 67.6 | Improved |
| increase beam size from 1 to 16 | Hierarchical Transformer · Timeouts | semantic accuracy: 12.6 -> 31.1 | Improved |
| increase beam size from 1 to 16 | Hierarchical Transformer · Smart Home | semantic accuracy: 19.0 -> 47.6 | Improved |
| increase beam size from 8 to 16 | Hierarchical Transformer · Smart Home | semantic accuracy: 33.3 -> 47.6 | Improved |
| increase beam size from 1 to 16 | Hierarchical Transformer · Testset realizable | semantic accuracy: 50.8 -> 70.7 | Improved |
| increase beam size from 1 to 16 | Hierarchical Transformer · Testset unrealizable | semantic accuracy: 55.4 -> 86.7 | Improved |
| evaluate unrealizable instead of realizable specifications | Hierarchical Transformer · Testset | semantic accuracy: 70.7 -> 86.7 | Improved |
| evaluate unrealizable instead of realizable specifications | Hierarchical Transformer · Testset | syntactic accuracy: 52.6 -> 39.0 | Hurt |
| use semantic instead of syntactic accuracy | Hierarchical Transformer · Testset | accuracy: 45.8 -> 78.7 | Improved |
| hierarchical instead of standard Transformer encoder (ablation) | Hierarchical Transformer · circuit synthesis | accuracy: approximately 10% | Improved |
| remove size restriction on Smart Home benchmark | Hierarchical Transformer · Smart Home | semantic accuracy: 47.6 -> 11.1 | Hurt |
Closest papers by meaning
- Towards Next-Generation Logic Synthesis: A Scalable Neural Circuit Generation Framework (NeurIPS 2024 · similarity 0.87)
- Circuit Transformer: A Transformer That Preserves Logical Equivalence (ICLR 2025 · similarity 0.86)
- Hierarchical Mixture of Experts: Generalizable Learning for High-Level Synthesis (AAAI 2025 · similarity 0.86)
- Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization (ICLR 2024 · similarity 0.85)
- Neural Model Checking (NeurIPS 2024 · similarity 0.85)
- A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design (ICML 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
