Research map / Label-efficient and robust learning / Recognition and long-tail
Neural Sketch Learning for Conditional Program Generation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Train on sketches and concretize them into programs instead of training directly on AML ASTs | GED and GSNN conditional program generation · Test data | overall prediction accuracy across M1-M5 | Helped |
| Train on sketches and concretize them into programs instead of training directly on AML ASTs | GED and GSNN conditional program generation · Test data | ill-formed sampled ASTs: 3% -> 0 | Helped |
| Use GED-Sk rather than GSNN-Sk | Sketch-based conditional program generation · Test data | overall prediction accuracy across M1-M5 | Helped |
Closest papers by meaning
- Neural Program Generation Modulo Static Analysis (NeurIPS 2021 · similarity 0.90)
- Learning to Infer Program Sketches (ICML 2019 · similarity 0.89)
- CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis (ICLR 2023 · similarity 0.88)
- Emergent Representations of Program Semantics in Language Models Trained on Programs (ICML 2024 · similarity 0.86)
- Program Synthesis via Test-Time Transduction (NeurIPS 2025 · similarity 0.86)
- HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis (NeurIPS 2024 · similarity 0.86)
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.