Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
A large-scale benchmark for few-shot program induction and synthesis
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 |
|---|---|---|---|
| Synthesize program then execute (synthesis) instead of directly predicting outputs (induction) (ablation) | BART-RobustFill · PROGRES | example and task accuracy | Helped |
| Add text context of overall program description (ablation) | BART-RobustFill · PROGRES | example and task accuracy: 16% relative example accuracy, 23% task accuracy | Helped |
| Increase number of examples from 5 to 10 (ablation) | BART-RobustFill · PROGRES | example and task accuracy | Helped |
| Use pretrained BART weights vs. training from scratch (ablation) | BART-RobustFill · PROGRES | example and task accuracy | Helped |
Closest papers by meaning
- Neural Program Meta-Induction (NeurIPS 2017 · similarity 0.87)
- PLANS: Neuro-Symbolic Program Learning from Videos (NeurIPS 2020 · similarity 0.87)
- A Unified Few-Shot Classification Benchmark to Compare Transfer and Meta Learning Approaches (NeurIPS 2021 · similarity 0.86)
- Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement (CVPR 2024 · similarity 0.86)
- Towards Synthesizing Complex Programs From Input-Output Examples (ICLR 2018 · similarity 0.86)
- Program Synthesis via Test-Time Transduction (NeurIPS 2025 · similarity 0.84)
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.