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 162 篇，第 1 / 4 页

1. CVPR 2023CaPriDe Learning: Confidential and Private Decentralized Learning Based on Encryption-Friendly Distillation Loss
2. CVPR 2023Handy: Towards a High Fidelity 3D Hand Shape and Appearance Model
3. CVPR 2023IMP: Iterative Matching and Pose Estimation With Adaptive Pooling
4. CVPR 2023Learning To Zoom and Unzoom
5. CVPR 2023Object Pose Estimation With Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagation
6. CVPR 2023ShapeClipper: Scalable 3D Shape Learning From Single-View Images via Geometric and CLIP-Based Consistency
7. CVPR 2023Understanding and Improving Features Learned in Deep Functional Maps
8. ICLR 2023FaiREE: fair classification with finite-sample and distribution-free guarantee
9. ICLR 2023Global Explainability of GNNs via Logic Combination of Learned Concepts
10. ICLR 2023Learning Soft Constraints From Constrained Expert Demonstrations
11. ICLR 2023Learning where and when to reason in neuro-symbolic inference
12. ICLR 2023Learning with Logical Constraints but without Shortcut Satisfaction
13. ICLR 2023LogicDP: Creating Labels for Graph Data via Inductive Logic Programming
14. ICLR 2023Timing is Everything: Learning to Act Selectively with Costly Actions and Budgetary Constraints
15. ICLR 2023Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic
16. ICLR 2023Weighted Clock Logic Point Process
17. ICML 2023A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel
18. ICML 2023Achieving Hierarchy-Free Approximation for Bilevel Programs with Equilibrium Constraints
19. ICML 2023Alternately Optimized Graph Neural Networks
20. ICML 2023Analyzing Convergence in Quantum Neural Networks: Deviations from Neural Tangent Kernels
21. ICML 2023BiBench: Benchmarking and Analyzing Network Binarization
22. ICML 2023Certified Robust Neural Networks: Generalization and Corruption Resistance
23. ICML 2023Controllable Neural Symbolic Regression
24. ICML 2023Distributed Linear Bandits under Communication Constraints
25. ICML 2023Does a Neural Network Really Encode Symbolic Concepts?
26. ICML 2023Effective Neural Topic Modeling with Embedding Clustering Regularization
27. ICML 2023Efficiently predicting high resolution mass spectra with graph neural networks
28. ICML 2023Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments
29. ICML 2023Eventual Discounting Temporal Logic Counterfactual Experience Replay
30. ICML 2023Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks
31. ICML 2023Generalization on the Unseen, Logic Reasoning and Degree Curriculum
32. ICML 2023Generalizing Neural Wave Functions
33. ICML 2023Hierarchical Neural Coding for Controllable CAD Model Generation
34. ICML 2023Implicit Neural Spatial Representations for Time-dependent PDEs
35. ICML 2023Improving Graph Neural Networks with Learnable Propagation Operators
36. ICML 2023Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic
37. ICML 2023Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks
38. ICML 2023Linear Time GPs for Inferring Latent Trajectories from Neural Spike Trains
39. ICML 2023Low Complexity Homeomorphic Projection to Ensure Neural-Network Solution Feasibility for Optimization over (Non-)Convex Set
40. ICML 2023Minimalistic Predictions to Schedule Jobs with Online Precedence Constraints
41. ICML 2023Minimum Width of Leaky-ReLU Neural Networks for Uniform Universal Approximation
42. ICML 2023Multi-channel Autobidding with Budget and ROI Constraints
43. ICML 2023Nearly Optimal Competitive Ratio for Online Allocation Problems with Two-sided Resource Constraints and Finite Requests
44. ICML 2023Neural signature kernels as infinite-width-depth-limits of controlled ResNets
45. ICML 2023NeuralSlice: Neural 3D Triangle Mesh Reconstruction via Slicing 4D Tetrahedral Meshes
46. ICML 2023Node Embedding from Neural Hamiltonian Orbits in Graph Neural Networks
47. ICML 2023On Regularization and Inference with Label Constraints
48. ICML 2023On the Expressive Power of Geometric Graph Neural Networks
49. ICML 2023On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization
50. ICML 2023On the Initialization of Graph Neural Networks

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。