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 34 篇，第 1 / 1 页

1. NeurIPS 2026$R^3$: 3D Reconstruction via Relative Regression
2. NeurIPS 2026Adversarially Attacking Symbolic Vocabulary Vulnerabilities In LLM Planners
3. NeurIPS 2026Bounds on Extrapolation across Phase Transitions with Generalized Regression
4. NeurIPS 2026Characterizing the Generalization Error of Random Feature Regression with Arbitrary Data-Augmentation
5. NeurIPS 2026Conformal Prediction for Distribution-to-Distribution Regression
6. NeurIPS 2026Continuous-depth Deep Gaussian Processes
7. NeurIPS 2026DASS: A Solver-Agnostic Dynamic Auxiliary Search Strategy for Symbolic Regression
8. NeurIPS 2026Data Diversity Drives the Emergence of Symbolic Mechanisms Supporting Abstract Reasoning
9. NeurIPS 2026Deep Heteroskedastic Regression: Post-Hoc Variance Estimation from Latent Representations
10. NeurIPS 2026EditFlowSR: Revisable Expression Generation for Symbolic Regression
11. NeurIPS 2026Efficient algorithms for linear regression with heteroskedastic errors
12. NeurIPS 2026End-to-End Verification of Neuro-symbolic Automata via Contrastive Logit-Gaps
13. NeurIPS 2026Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension
14. NeurIPS 2026Geometry-Constrained Kolmogorov–Arnold Networks: Learning Edge Geometry via Banach Duality
15. NeurIPS 2026In-Context Benign Overfitting: A Feature-Selection Model in Linear Regression ICL
16. NeurIPS 2026Interpretable Relational Inference with LLM-Guided Symbolic Dynamics Modeling
17. NeurIPS 2026Just Ramp-Up: Debiasing Regression-based Estimator for A/B Tests under Network Interference
18. NeurIPS 2026Kernel Value Regression in Offline Reinforcement Learning
19. NeurIPS 2026Learning Optimal Transport Plans Via Autoregressive Token Regression
20. NeurIPS 2026Learning with Synthetic Data via SGD in High-Dimensional Linear Regression
21. NeurIPS 2026Multiple Descent of Generalization Curve for Optimally Regularized Ridge Regression
22. NeurIPS 2026NesyProAct: Proactive Neural-Symbolic Control for Web Agents
23. NeurIPS 2026Optimal Linear Regression Without a Variance
24. NeurIPS 2026Pooling Versus Ensembling for Ridge Regression Under Covariate Shift
25. NeurIPS 2026Position: The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Models
26. NeurIPS 2026Regret-Optimal Wasserstein-Robust Regression
27. NeurIPS 2026RL-Guided Contraction of Symbolic Tensor Networks for Quantum Circuit Equivalence
28. NeurIPS 2026Sparse Attention as Compact Kernel Regression
29. NeurIPS 2026Sup-Norm Error under Proportional Asymptotics: Phase Transitions under Linear Regression
30. NeurIPS 2026Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology
31. NeurIPS 2026The Minimax Rate of Online Isotonic Regression on Product Orders
32. NeurIPS 2026Transfer Learning of Linear Regression with Multiple Pretrained Models: Benefiting from More Pretrained Models via Overparameterization Debiasing
33. NeurIPS 2026Umbilic Multinomial Logistic Regression
34. NeurIPS 2026Very Fast Bayesian Additive Regression Trees on GPU

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。