Research map / Label-efficient and robust learning / Recognition and long-tail
Learning abstract structure for drawing by efficient motor program induction
Lucas Tian, Kevin Ellis, Marta Kryven, Josh Tenenbaum
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 |
|---|---|---|---|
| add program induction (abstract compositional programs) on top of learned motor cost (ablation) | Hybrid model · human-model similarity on test drawing tasks | similarity to human behavior | Improved |
| add motor-cost reweighting of trajectories to program induction (ablation) | Program Induction model · human-model similarity on test drawing tasks | similarity to human behavior | Improved |
| train program induction model on drawing tasks (vs untrained baseline) | program induction model · Test drawing tasks | ability to solve test tasks | Improved |
Closest papers by meaning
- Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks (NeurIPS 2024 · similarity 0.86)
- SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal Models (ICLR 2026 · similarity 0.85)
- SketchAgent: Language-Driven Sequential Sketch Generation (CVPR 2025 · similarity 0.84)
- PotARCin: Multi-Dimensional Evaluation of Skill Acquisition in Abstract Reasoning Tasks (NeurIPS 2026 · similarity 0.84)
- What Sketch Explainability Really Means for Downstream Tasks? (CVPR 2024 · similarity 0.84)
- Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models (NeurIPS 2024 · 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.
