符号回归论文趋势 2023–2026

主要结论

• 符号回归论文从 2023 年的 63 篇增长到 2026 年的 97 篇，三年间扩大到约 1.5 倍。
• NeurIPS 是发符号回归论文最多的会议，2023–2026 年共 118 篇，占四个会议总量的 37%。
• 交叉方向里涨得最快的是理论 · learning theory：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 10 篇。
• 在「程序综合」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的定理证明是 13 倍，符号回归是 1.5 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026Conformal Prediction for Distribution-to-Distribution Regression
• ICML 2026Approximation Bounds for Transformer Networks with Application to Regression
• ICLR 2026Fast Estimation of Wasserstein Distances via Regression on Sliced Wasserstein Distances
• CVPR 2026CoLoR The Devil is in Scene Coordinate Regression for Large-Scale
• NeurIPS 2025Ascent Fails to Forget
• ICML 2025Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression
• ICLR 2025A Graph Enhanced Symbolic Discovery Framework For Efficient Logic Optimization
• CVPR 2025R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization
• NeurIPS 2024Distributed Sparse Regression via Penalization
• ICML 2024$H$-Consistency Guarantees for Regression
• ICLR 2024Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression Tasks
• CVPR 2024Map-Relative Pose Regression for Visual Re-Localization
• NeurIPS 2023Collaboratively Learning Linear Models with Structured Missing Data
• ICML 2023A Nearly-Optimal Bound for Fast Regression with $\ell_\infty$ Guarantee
• ICLR 2023Fast Nonlinear Vector Quantile Regression
• CVPR 2023DistilPose: Tokenized Pose Regression With Heatmap Distillation
• NeurIPS 2026DASS: A Solver-Agnostic Dynamic Auxiliary Search Strategy for Symbolic Regression
• ICML 2026AutoNumerics-Zero: Automated Discovery of State-of-the-Art Mathematical Functions
• ICLR 2026GenSR: Symbolic regression based on equation generative space
• CVPR 2026Sparse-View Localization via Online Neural 3D Regression

全部符号回归论文

共 97 篇，第 1 / 2 页

1. CVPR 2026CoLoR The Devil is in Scene Coordinate Regression for Large-Scale
2. CVPR 2026Keep it SymPL Symbolic Projective Layout for Allocentric Spatial Reasoning
3. CVPR 2026Sparse-View Localization via Online Neural 3D Regression
4. ICLR 2026A Hierarchical Circuit Symbolic Discovery Framework for Efficient Logic Optimization
5. ICLR 2026Bayesian Post Training Enhancement of Regression Models with Calibrated Rankings
6. ICLR 2026Compositional Neuro-Symbolic Concepts in Neural Activities
7. ICLR 2026Continuous multinomial logistic regression for neural decoding
8. ICLR 2026Covariate-Guided Clusterwise Linear Regression for Generalization to Unseen Data
9. ICLR 2026Deep Learning for Subspace Regression
10. ICLR 2026Differentially Private Two-Stage Gradient Descent for Instrumental Variable Regression
11. ICLR 2026Direct Doubly Robust Estimation of Conditional Quantile Contrasts
12. ICLR 2026Distributionally Robust Linear Regression with Block Lewis Weights
13. ICLR 2026Fast Estimation of Wasserstein Distances via Regression on Sliced Wasserstein Distances
14. ICLR 2026GenSR: Symbolic regression based on equation generative space
15. ICLR 2026HATSolver: Learning Gröbner Bases with Hierarchical Attention Transformers
16. ICLR 2026Improved $\ell_{p}$ Regression via Iteratively Reweighted Least Squares
17. ICLR 2026Inferring the Invisible: Neuro-Symbolic Rule Discovery for Missing Value Imputation
18. ICLR 2026Learning under Quantization for High-Dimensional Linear Regression
19. ICLR 2026Neural Optimal Transport Meets Multivariate Conformal Prediction
20. ICLR 2026Non-Asymptotic Analysis of Efficiency in Conformalized Regression
21. ICLR 2026On Coreset for LASSO Regression Problem with Sensitivity Sampling
22. ICLR 2026Predicting Kernel Regression Learning Curves from Only Raw Data Statistics
23. ICLR 2026Programming by Backprop: Learning Behaviour from Symbolic Descriptions
24. ICLR 2026Robust Equation Structure learning with Adaptive Refinement
25. ICLR 2026Scaling Laws of SignSGD in Linear Regression: When Does It Outperform SGD?
26. ICLR 2026SR-Scientist: Scientific Equation Discovery With Agentic AI
27. ICLR 2026TESSAR: Geometry-Aware Active Regression via Dynamic Voronoi Tessellation
28. ICML 2026Accelerating Regression Tasks with Quantum Algorithms
29. ICML 2026Active Regression for Single-Index Models with Unknown Link Functions
30. ICML 2026Approximation Bounds for Transformer Networks with Application to Regression
31. ICML 2026AutoNumerics-Zero: Automated Discovery of State-of-the-Art Mathematical Functions
32. ICML 2026Beyond Accuracy and Complexity: The Effective Information Criterion for Structurally Stable Symbolic Regression
33. ICML 2026Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning
34. ICML 2026Breaking the Simplification Bottleneck in Amortized Neural Symbolic Regression
35. ICML 2026Colorful Pinball: Density-Weighted Quantile Regression for Conditional Guarantee of Conformal Prediction
36. ICML 2026Contrastive Symbolic Regression: Aligned Representations, Adaptive Prediction, and Diverse Ensembles
37. ICML 2026Deep Neural Network Regression with Functional Covariates
38. ICML 2026Deep Single-Index Fréchet Regression
39. ICML 2026Estimating Continuous Treatment Effects with Two-Stage Kernel Ridge Regression
40. ICML 2026Hard labels sampled from sparse targets mislead rotation invariant algorithms
41. ICML 2026Higher-Order Certified Robustness for Regression
42. ICML 2026How Hard Is Science?
43. ICML 2026Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular Feedback
44. ICML 2026Learning Randomized Reductions
45. ICML 2026Learning Treatment Representations for Downstream Instrumental Variable Regression
46. ICML 2026Must All Negatives Be Pushed Away Equally? Uncertainty-Aware Cross-View Geo-Localization via Normal Inverse Gamma Distribution
47. ICML 2026Neural–Evolutionary Symbolic Regression with Global Constraints: Constraint-Aware Decoding and Reward Shaping
48. ICML 2026Neuro-Symbolic AI for Analytical Solutions of Differential Equations
49. ICML 2026Nonparametric Distribution Regression Re-calibration
50. ICML 2026On Uniform Error Bounds for Kernel Regression under Non-Gaussian Noise

常见问题

2023–2026 年四大会议一共有多少篇符号回归论文？

共 316 篇，按年份分别是 2023 年 63 篇、2024 年 81 篇、2025 年 75 篇、2026 年 97 篇。

NeurIPS 2026 有多少篇符号回归论文？

NeurIPS 2026 有 34 篇符号回归论文，上一届是 30 篇。

ICLR 2026 有多少篇符号回归论文？

ICLR 2026 有 24 篇符号回归论文，上一届是 22 篇。

ICML 2026 有多少篇符号回归论文？

ICML 2026 有 36 篇符号回归论文，上一届是 21 篇。

CVPR 2026 有多少篇符号回归论文？

CVPR 2026 有 3 篇符号回归论文，上一届是 2 篇。

哪个会议的符号回归论文最多？

NeurIPS，2023–2026 年共 118 篇。