Symbolic Regression papers, 2023–2026

Key findings

• Symbolic Regression went from 63 papers in 2023 to 97 in 2026, roughly 1.5x in three years.
• NeurIPS publishes the most Symbolic Regression work: 118 papers from 2023 to 2026, 37% of the four-venue total.
• The fastest-growing overlap is with Theory · learning theory: papers tagged with both rose from 1 in 2023 to 10 in 2026.
• Among the 5 topics under Program Synthesis, it ranks #1 by 2026 paper count; the fastest grower in the group, Theorem Proving, is up 13x versus 1.5x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Symbolic Regression papers

316 papers, page 3 of 7

101. ICLR 2025Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton Influence
102. ICLR 2025Attention layers provably solve single-location regression
103. ICLR 2025Bayesian Image Regression with Soft-thresholded Conditional Autoregressive Prior
104. ICLR 2025Benign Overfitting in Out-of-Distribution Generalization of Linear Models
105. ICLR 2025Can Large Language Models Understand Symbolic Graphics Programs?
106. ICLR 2025Discovering Group Structures via Unitary Representation Learning
107. ICLR 2025Distribution-Free Data Uncertainty for Neural Network Regression
108. ICLR 2025Implicit Bias of Mirror Flow for Shallow Neural Networks in Univariate Regression
109. ICLR 2025Improving Deep Regression with Tightness
110. ICLR 2025KinFormer: Generalizable Dynamical Symbolic Regression for Catalytic Organic Reaction Kinetics
111. ICLR 2025LLM-SR: Scientific Equation Discovery via Programming with Large Language Models
112. ICLR 2025Near-optimal Active Regression of Single-Index Models
113. ICLR 2025No Equations Needed: Learning System Dynamics Without Relying on Closed-Form ODEs
114. ICLR 2025ParFam -- (Neural Guided) Symbolic Regression via Continuous Global Optimization
115. ICLR 2025RAG-SR: Retrieval-Augmented Generation for Neural Symbolic Regression
116. ICLR 2025RegMix: Data Mixture as Regression for Language Model Pre-training
117. ICLR 2025State Space Models are Provably Comparable to Transformers in Dynamic Token Selection
118. ICLR 2025Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length
119. ICLR 2025Towards Learning High-Precision Least Squares Algorithms with Sequence Models
120. ICLR 2025Transformers Handle Endogeneity in In-Context Linear Regression
121. ICLR 2025TRENDy: Temporal Regression of Effective Nonlinear Dynamics
122. ICML 2025A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models
123. ICML 2025Ab Initio Nonparametric Variable Selection for Scalable Symbolic Regression with Large $p$
124. ICML 2025Batch List-Decodable Linear Regression via Higher Moments
125. ICML 2025Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression
126. ICML 2025Curvature Enhanced Data Augmentation for Regression
127. ICML 2025Dataflow-Guided Neuro-Symbolic Language Models for Type Inference
128. ICML 2025Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements
129. ICML 2025Exploring Invariance in Images through One-way Wave Equations
130. ICML 2025Fast Min-$\epsilon$ Segmented Regression using Constant-Time Segment Merging
131. ICML 2025FEAT-KD: Learning Concise Representations for Single and Multi-Target Regression via TabNet Knowledge Distillation
132. ICML 2025Fully Heteroscedastic Count Regression with Deep Double Poisson Networks
133. ICML 2025Gradient Aligned Regression via Pairwise Losses
134. ICML 2025Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update
135. ICML 2025Learning Curves of Stochastic Gradient Descent in Kernel Regression
136. ICML 2025LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models
137. ICML 2025Meta Optimality for Demographic Parity Constrained Regression via Post-Processing
138. ICML 2025On Volume Minimization in Conformal Regression
139. ICML 2025Pareto-Optimal Fronts for Benchmarking Symbolic Regression Algorithms
140. ICML 2025PRIME: Deep Imbalanced Regression with Proxies
141. ICML 2025Sharp Generalization for Nonparametric Regression by Over-Parameterized Neural Networks: A Distribution-Free Analysis in Spherical Covariate
142. ICML 2025Theoretical Limitations of Ensembles in the Age of Overparameterization
143. NeurIPS 2025A Closer Look at NTK Alignment: Linking Phase Transitions in Deep Image Regression
144. NeurIPS 2025A learnability analysis on neuro-symbolic learning
145. NeurIPS 2025Adversarial Robustness of Nonparametric Regression
146. NeurIPS 2025Ascent Fails to Forget
147. NeurIPS 2025Compact Memory for Continual Logistic Regression
148. NeurIPS 2025Computational Efficiency under Covariate Shift in Kernel Ridge Regression
149. NeurIPS 2025Discovering Symbolic Partial Differential Equation by Abductive Learning
150. NeurIPS 2025Enhancing Deep Batch Active Learning for Regression with Imperfect Data Guided Selection

FAQ

How many Symbolic Regression papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

316 in total: 63 in 2023, 81 in 2024, 75 in 2025, 97 in 2026.

How many Symbolic Regression papers are at NeurIPS 2026?

NeurIPS 2026 has 34 Symbolic Regression papers, versus 30 the year before.

How many Symbolic Regression papers are at ICLR 2026?

ICLR 2026 has 24 Symbolic Regression papers, versus 22 the year before.

How many Symbolic Regression papers are at ICML 2026?

ICML 2026 has 36 Symbolic Regression papers, versus 21 the year before.

How many Symbolic Regression papers are at CVPR 2026?

CVPR 2026 has 3 Symbolic Regression papers, versus 2 the year before.

Which conference publishes the most Symbolic Regression papers?

NeurIPS, with 118 papers from 2023 to 2026.