Research map / Label-efficient and robust learning / Domain adaptation and generalization
Cross-Domain Demo-to-Code via Neurosymbolic Counterfactual Reasoning
Jooyoung Kim, Wonje Choi, Younguk Song, Honguk Woo
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 verification of alternative actions (ablation) | NeSyCR · Sim, combined factor ablation (medium complexity) | success rate (SR, %): 68.42 -> 50.00 | Improved |
| add counterfactual identification (ablation) | NeSyCR · Sim, combined factor ablation (medium complexity) | success rate (SR, %): 68.42 -> 47.37 | Improved |
| add both counterfactual identification and verification (ablation) | NeSyCR · Sim, combined factor ablation (medium complexity) | success rate (SR, %): 68.42 -> 39.47 | Improved |
| add symbolic world model (ablation) | NeSyCR · Sim, combined factor ablation (medium complexity) | success rate (SR, %): 68.42 -> 34.21 | Improved |
| add symbolic world model (ablation) | NeSyCR · Sim, combined factor ablation (medium complexity) | goal condition (GC, %): 84.21 -> 67.54 | Improved |
| add alternative-action verification (ablation) | NeSyCR · Sim, combined factor ablation (medium complexity) | procedure deviation (PD): 6.60 -> 14.65 | Improved |
| neurosymbolic counterfactual adaptation instead of Demo2Code | NeSyCR vs Demo2Code · Real-world Franka, combined factor (medium complexity) | success rate (SR, %): 0.00 -> 87.50 | Improved |
| neurosymbolic counterfactual adaptation instead of Statler | NeSyCR vs Statler · Real-world Franka, combined factor (medium complexity) | success rate (SR, %): 50.00 -> 87.50 | Improved |
| neurosymbolic counterfactual adaptation instead of GPT4V-Robotics | NeSyCR vs GPT4V-Robotics · Real-world Franka, combined factor (medium complexity) | goal condition (GC, %): 75.00 -> 98.21 | Improved |
| neurosymbolic counterfactual adaptation instead of Statler | NeSyCR vs Statler · Sim, obstruction + object affordance (high complexity) | success rate (SR, %): 5.00 -> 60.00 | Improved |
| neurosymbolic counterfactual adaptation instead of LLM-DM | NeSyCR vs LLM-DM · Sim, obstruction + object affordance (medium complexity) | success rate (SR, %): 20.00 -> 75.00 | Improved |
| increase task complexity gap from low to high | NeSyCR · Sim, obstruction + object affordance | success rate (SR, %): 86.67 -> 60.00 | Hurt |
Closest papers by meaning
- UniDomain: Pretraining a Unified PDDL Domain from Real-World Demonstrations for Generalizable Robot Task Planning (NeurIPS 2025 · similarity 0.88)
- Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning (NeurIPS 2025 · similarity 0.87)
- CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation (ICML 2026 · similarity 0.86)
- RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis (ICML 2024 · similarity 0.86)
- NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains (ICLR 2025 · similarity 0.86)
- RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation (NeurIPS 2025 · 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.
