Research map / Probabilistic and scientific modeling / Molecules and proteins
Accurate Interpolation for Scattered Data through Hierarchical Residual Refinement
Shizhe Ding, Boyang Xia, Dongbo Bu
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 |
|---|---|---|---|
| hierarchical decreasing K instead of fixed K=K(1) (ablation) | HINT · PTV | MSE (x10^-3): 4.791 -> 3.507 | Improved |
| hierarchical decreasing K instead of fixed K=K(0) (ablation) | HINT · Perlin | MSE (x10^-5): 7.017 -> 5.848 | Improved |
| hierarchical decreasing K instead of fixed K=K(1) (ablation) | HINT · TFRD-ADlet | MAE (x10^-3): 2.975 -> 1.761 | Improved |
| add one residual block (1 -> 2 blocks) (ablation) | HINT · Perlin | MSE (x10^-5): 21.453 -> 11.279 | Improved |
| increase blocks from 4 to 5 (ablation) | HINT · Perlin | MSE (x10^-5): 5.848 -> 6.224 | Hurt |
| increase blocks from 4 to 5 (ablation) | HINT · PTV | MSE (x10^-3): 3.507 -> 3.618 | No clear effect |
Closest papers by meaning
- Understanding Layer Patching in Model Size Interpolation (NeurIPS 2026 · similarity 0.83)
- The Price of Linear Time: Error Analysis of Structured Kernel Interpolation (ICML 2025 · similarity 0.82)
- Interpolating Neural Network-Tensor Decomposition (INN-TD): a scalable and interpretable approach for large-scale physics-based problems (ICML 2025 · similarity 0.82)
- High-Resolution Frame Interpolation with Patch-based Cascaded Diffusion (AAAI 2025 · similarity 0.81)
- Stochastic Interpolants via Conditional Dependent Coupling (NeurIPS 2026 · similarity 0.81)
- Hierarchical Uncertainty Exploration via Feedforward Posterior Trees (NeurIPS 2024 · similarity 0.81)
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.
