逻辑与神经论文趋势 2023–2026

主要结论

• 逻辑与神经论文从 2023 年的 162 篇降到 2026 年的 86 篇，热度在回落。
• NeurIPS 是发逻辑与神经论文最多的会议，2023–2026 年共 173 篇，占四个会议总量的 47%。
• 交叉方向里涨得最快的是社会层面 · accountability transparency and interpretability：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 8 篇。
• 在「神经符号」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的数学推理是 10 倍，逻辑与神经是 0.5 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 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

全部逻辑与神经论文

共 99 篇，第 2 / 2 页

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?

常见问题

2023–2026 年四大会议一共有多少篇逻辑与神经论文？

共 366 篇，按年份分别是 2023 年 162 篇、2024 年 64 篇、2025 年 54 篇、2026 年 86 篇。

NeurIPS 2026 有多少篇逻辑与神经论文？

NeurIPS 2026 有 32 篇逻辑与神经论文，上一届是 23 篇。

ICLR 2026 有多少篇逻辑与神经论文？

ICLR 2026 有 20 篇逻辑与神经论文，上一届是 11 篇。

ICML 2026 有多少篇逻辑与神经论文？

ICML 2026 有 25 篇逻辑与神经论文，上一届是 12 篇。

CVPR 2026 有多少篇逻辑与神经论文？

CVPR 2026 有 9 篇逻辑与神经论文，上一届是 8 篇。

哪个会议的逻辑与神经论文最多？

NeurIPS，2023–2026 年共 173 篇。