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 366 篇，第 3 / 8 页

101. ICLR 2025Is uniform expressivity too restrictive? Towards efficient expressivity of GNNs
102. ICLR 2025Optimal Flow Transport and its Entropic Regularization: a GPU-friendly Matrix Iterative Algorithm for Flow Balance Satisfaction
103. ICLR 2025Point-based Instance Completion with Scene Constraints
104. ICLR 2025Towards a Complete Logical Framework for GNN Expressiveness
105. ICLR 2025Unsupervised Disentanglement of Content and Style via Variance-Invariance Constraints
106. ICML 2025Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models
107. ICML 2025Counterfactual Graphical Models: Constraints and Inference
108. ICML 2025Evolving Minds: Logic-Informed Inference from Temporal Action Patterns
109. ICML 2025Grammar-Forced Translation of Natural Language to Temporal Logic using LLMs
110. ICML 2025Improving Out-of-Distribution Detection with Markov Logic Networks
111. ICML 2025Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence
112. ICML 2025Learning Parametric Distributions from Samples and Preferences
113. ICML 2025Multinoulli Extension: A Lossless Yet Effective Probabilistic Framework for Subset Selection over Partition Constraints
114. ICML 2025Online Learning with Unknown Constraints
115. ICML 2025Regret-Free Reinforcement Learning for Temporal Logic Specifications
116. ICML 2025RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization
117. ICML 2025Understanding the Logic of Direct Preference Alignment through Logic
118. NeurIPS 2025Automaton Constrained Q-Learning
119. NeurIPS 2025Characterizing the Expressivity of Fixed-Precision Transformer Language Models
120. NeurIPS 2025Codifying Character Logic in Role-Playing
121. NeurIPS 2025Constrained Best Arm Identification
122. NeurIPS 2025DualFocus: Depth from Focus with Spatio-Focal Dual Variational Constraints
123. NeurIPS 2025Efficient Allocation of Working Memory Resource for Utility Maximization in Humans and Recurrent Neural Networks
124. NeurIPS 2025Embeddings as Probabilistic Equivalence in Logic Programs
125. NeurIPS 2025Enforcing convex constraints in Graph Neural Networks
126. NeurIPS 2025ESCORT: Efficient Stein-variational and Sliced Consistency-Optimized Temporal Belief Representation for POMDPs
127. NeurIPS 2025Feasibility-Aware Decision-Focused Learning for Predicting Parameters in the Constraints
128. NeurIPS 2025Functional Matching of Logic Subgraphs: Beyond Structural Isomorphism
129. NeurIPS 2025Imitation Learning with Temporal Logic Constraints
130. NeurIPS 2025Knee-Deep in C-RASP: A Transformer Depth Hierarchy
131. NeurIPS 2025LLM Query Scheduling with Prefix Reuse and Latency Constraints
132. NeurIPS 2025Logic.py: Bridging the Gap between LLMs and Constraint Solvers
133. NeurIPS 2025Logical Expressiveness of Graph Neural Networks with Hierarchical Node Individualization
134. NeurIPS 2025Mind the Gap: Removing the Discretization Gap in Differentiable Logic Gate Networks
135. NeurIPS 2025Model Reconciliation via Cost-Optimal Explanations in Probabilistic Logic Programming
136. NeurIPS 2025NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
137. NeurIPS 2025Neural Rule Lists: Learning Discretizations, Rules, and Order in One Go
138. NeurIPS 2025On Logic-based Self-Explainable Graph Neural Networks
139. NeurIPS 2025The Logical Expressiveness of Temporal GNNs via Two-Dimensional Product Logics
140. NeurIPS 2025Who You Are Matters: Bridging Interests and Social Roles via LLM-Enhanced Logic Recommendation
141. CVPR 2024An N-Point Linear Solver for Line and Motion Estimation with Event Cameras
142. CVPR 2024Beyond Textual Constraints: Learning Novel Diffusion Conditions with Fewer Examples
143. CVPR 2024FLHetBench: Benchmarking Device and State Heterogeneity in Federated Learning
144. CVPR 2024Global and Local Prompts Cooperation via Optimal Transport for Federated Learning
145. CVPR 2024HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video
146. CVPR 2024MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraints
147. CVPR 2024Objects as Volumes: A Stochastic Geometry View of Opaque Solids
148. CVPR 2024Predicated Diffusion: Predicate Logic-Based Attention Guidance for Text-to-Image Diffusion Models
149. CVPR 2024Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation
150. CVPR 2024SpiderMatch: 3D Shape Matching with Global Optimality and Geometric Consistency

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。