Logic and Neural papers, 2023–2026

Key findings

• Logic and Neural fell from 162 papers in 2023 to 86 in 2026, so interest is cooling.
• NeurIPS publishes the most Logic and Neural work: 173 papers from 2023 to 2026, 47% of the four-venue total.
• The fastest-growing overlap is with Social aspects · accountability transparency and interpretability: papers tagged with both rose from 1 in 2023 to 8 in 2026.
• Among the 5 topics under Neurosymbolic AI, it ranks #2 by 2026 paper count; the fastest grower in the group, Mathematical Reasoning, is up 10x versus 0.5x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026B$^3$-PWL: GPU-Batched Branch-and-Bound for Piecewise-Linear Optimization with SOS2 Constraints
• ICML 2026Length Generalization Bounds for Transformers
• ICLR 2026From Neural Networks to Logical Theories: The Correspondence between Fibring Modal Logics and Fibring Neural Networks
• CVPR 2026Med-CMR A Fine-Grained Benchmark Integrating Visual Evidence and Clinical Logic
• NeurIPS 2025Characterizing the Expressivity of Fixed-Precision Transformer Language Models
• ICML 2025Counterfactual Graphical Models: Constraints and Inference
• ICLR 2025Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraints
• CVPR 2025Learning Affine Correspondences by Integrating Geometric Constraints
• NeurIPS 2024Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints
• ICML 2024A Field Guide for Pacing Budget and ROS Constraints
• ICLR 2024LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints
• CVPR 2024MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraints
• NeurIPS 2023Aligning Gradient and Hessian for Neural Signed Distance Function
• ICML 2023Eventual Discounting Temporal Logic Counterfactual Experience Replay
• ICLR 2023Global Explainability of GNNs via Logic Combination of Learned Concepts
• CVPR 2023Handy: Towards a High Fidelity 3D Hand Shape and Appearance Model
• NeurIPS 2026Batched Stochastic Linear Bandits with 1-Bit Communication Constraints
• ICML 2026KANFIS: A Neuro-Symbolic Framework for Interpretable and Uncertainty-Aware Learning
• ICLR 2026The Logical Expressiveness of Topological Neural Networks
• CVPR 2026NeuroRule Bridging Vision and Logic with Differentiable Rule Induction

All Logic and Neural papers

99 papers, page 2 of 2

51. NeurIPS 2023Nearly Optimal VC-Dimension and Pseudo-Dimension Bounds for Deep Neural Network Derivatives
52. NeurIPS 2023Neural approximation of Wasserstein distance via a universal architecture for symmetric and factorwise group invariant functions
53. NeurIPS 2023Neural Circuits for Fast Poisson Compressed Sensing in the Olfactory Bulb
54. NeurIPS 2023Neural Frailty Machine: Beyond proportional hazard assumption in neural survival regressions
55. NeurIPS 2023Neural Functional Transformers
56. NeurIPS 2023Neural Image Compression: Generalization, Robustness, and Spectral Biases
57. NeurIPS 2023Neural Lyapunov Control for Discrete-Time Systems
58. NeurIPS 2023Neural Oscillators are Universal
59. NeurIPS 2023Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features
60. NeurIPS 2023Neural Processes with Stability
61. NeurIPS 2023Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data
62. NeurIPS 2023Neural Sculpting: Uncovering hierarchically modular task structure in neural networks through pruning and network analysis
63. NeurIPS 2023Neural-Logic Human-Object Interaction Detection
64. NeurIPS 2023NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries
65. NeurIPS 2023Norm-based Generalization Bounds for Sparse Neural Networks
66. NeurIPS 2023NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF
67. NeurIPS 2023On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective
68. NeurIPS 2023Optimization and Bayes: A Trade-off for Overparameterized Neural Networks
69. NeurIPS 2023Permutation Equivariant Neural Functionals
70. NeurIPS 2023Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets
71. NeurIPS 2023Provably Bounding Neural Network Preimages
72. NeurIPS 2023Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond
73. NeurIPS 2023ReDS: Offline RL With Heteroskedastic Datasets via Support Constraints
74. NeurIPS 2023ReHLine: Regularized Composite ReLU-ReHU Loss Minimization with Linear Computation and Linear Convergence
75. NeurIPS 2023ReTR: Modeling Rendering Via Transformer for Generalizable Neural Surface Reconstruction
76. NeurIPS 2023Riemannian Laplace approximations for Bayesian neural networks
77. NeurIPS 2023Riemannian Residual Neural Networks
78. NeurIPS 2023Sheaf Hypergraph Networks
79. NeurIPS 2023Should Under-parameterized Student Networks Copy or Average Teacher Weights?
80. NeurIPS 2023Simplicity Bias in 1-Hidden Layer Neural Networks
81. NeurIPS 2023Simplifying Neural Network Training Under Class Imbalance
82. NeurIPS 2023Slow and Weak Attractor Computation Embedded in Fast and Strong E-I Balanced Neural Dynamics
83. NeurIPS 2023SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding
84. NeurIPS 2023Soft-Unification in Deep Probabilistic Logic
85. NeurIPS 2023Spectral Evolution and Invariance in Linear-width Neural Networks
86. NeurIPS 2023Spiking PointNet: Spiking Neural Networks for Point Clouds
87. NeurIPS 2023StEik: Stabilizing the Optimization of Neural Signed Distance Functions and Finer Shape Representation
88. NeurIPS 2023Structure from Duplicates: Neural Inverse Graphics from a Pile of Objects
89. NeurIPS 2023Structured Neural-PI Control with End-to-End Stability and Output Tracking Guarantees
90. NeurIPS 2023TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery
91. NeurIPS 2023Towards Label Position Bias in Graph Neural Networks
92. NeurIPS 2023Train Once and Explain Everywhere: Pre-training Interpretable Graph Neural Networks
93. NeurIPS 2023Training Neural Networks is NP-Hard in Fixed Dimension
94. NeurIPS 2023Training shallow ReLU networks on noisy data using hinge loss: when do we overfit and is it benign?
95. NeurIPS 2023Training Transformers with 4-bit Integers
96. NeurIPS 2023Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers
97. NeurIPS 2023Universal Prompt Tuning for Graph Neural Networks
98. NeurIPS 2023UP-NeRF: Unconstrained Pose Prior-Free Neural Radiance Field
99. NeurIPS 2023When Do Neural Nets Outperform Boosted Trees on Tabular Data?

FAQ

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

366 in total: 162 in 2023, 64 in 2024, 54 in 2025, 86 in 2026.

How many Logic and Neural papers are at NeurIPS 2026?

NeurIPS 2026 has 32 Logic and Neural papers, versus 23 the year before.

How many Logic and Neural papers are at ICLR 2026?

ICLR 2026 has 20 Logic and Neural papers, versus 11 the year before.

How many Logic and Neural papers are at ICML 2026?

ICML 2026 has 25 Logic and Neural papers, versus 12 the year before.

How many Logic and Neural papers are at CVPR 2026?

CVPR 2026 has 9 Logic and Neural papers, versus 8 the year before.

Which conference publishes the most Logic and Neural papers?

NeurIPS, with 173 papers from 2023 to 2026.