Research map / Image generation / Fast diffusion sampling
MOD-SR: Unifying Multimodal Learning and Direct Optimization with Gradient-Guided Diffusion Model for Symbolic Regression
Chuyang Xiang, Yichen Wei, Junchi Yan
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 MSE gradient guidance at inference (ablation) | MOD-SR · Standard benchmarks average | R2: 0.968 -> 0.976 | Improved |
| add length gradient guidance at inference (ablation) | MOD-SR · Standard benchmarks average | complexity (nodes): 17.0 -> 16.0 | Improved |
| add MSE gradient guidance (ablation) | MOD-SR · Constant | R2: 0.929 -> 0.983 | Improved |
| add MSE gradient guidance (ablation) | MOD-SR · Keijzer, Koza, Livermore, R | R2: Keijzer 0.970 -> 0.970 | No clear effect |
| add representation alignment during training (ablation) | MOD-SR · training dynamics | convergence and final performance | Improved |
| use random subtree masking instead of full-tree optimization in guidance (ablation) | MOD-SR · hard cases | fit | Improved |
| use native perturbation with gradient guidance instead of GP or LSO post-processing | MOD-SR · Standard benchmarks | R2: Keijzer 0.819 (SNIP LSO) -> 0.983 | Improved |
| use token-wise embedding space instead of pooled global vector (ablation) | SNIP encoder · expression reconstruction | accuracy: 0.6518 -> 0.9997 | Improved |
| enable gradient guidance at inference (ablation) | MOD-SR · Single-instance runtime | runtime: 2.80s -> 18.44s | Hurt |
Closest papers by meaning
- SMILE: Bridging Continuous Optimization and Discrete Symbolic Recovery (NeurIPS 2026 · similarity 0.86)
- Ab Initio Nonparametric Variable Selection for Scalable Symbolic Regression with Large $p$ (ICML 2025 · similarity 0.86)
- MMaDA: Multimodal Large Diffusion Language Models (NeurIPS 2025 · similarity 0.86)
- ParFam -- (Neural Guided) Symbolic Regression via Continuous Global Optimization (ICLR 2025 · similarity 0.85)
- Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length (ICLR 2025 · similarity 0.85)
- SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training (ICLR 2024 · similarity 0.85)
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.
