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 1 / 8 页

1. CVPR 2026Federated Active Learning Under Extreme Non-IID and Global Class Imbalance
2. CVPR 2026FUSER Feed-Forward Multiview 3D Registration Transformer and SE3N Diffusion Refinement
3. CVPR 2026High-Quality and Efficient Turbulence Mitigation with Events
4. CVPR 2026Lifelong Imitation Learning with Multimodal Latent Replay and Incremental Adjustment
5. CVPR 2026Med-CMR A Fine-Grained Benchmark Integrating Visual Evidence and Clinical Logic
6. CVPR 2026NeuroRule Bridging Vision and Logic with Differentiable Rule Induction
7. CVPR 2026Plug-and-Play Incomplete Multi-View Clustering via Janus-Faced Affinity Learning with Topology
8. CVPR 2026RealAppiance Let High-fidelity Appliance Assets Controllable and Workable as Aligned
9. CVPR 2026Understanding Temporal Logic Consistency in Video-Language Models through Cross-Modal Attention
10. ICLR 2026A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic
11. ICLR 2026Automating the Refinement of Reinforcement Learning Specifications
12. ICLR 2026Bandits with Single-Peaked Preferences and Limited Resources
13. ICLR 2026Compose and Fuse: Revisiting the Foundational Bottlenecks in Multimodal Reasoning
14. ICLR 2026Convergence Analysis of Tsetlin Machines under Noise-Free and Noisy Training Conditions: from $2$ Bits to $k$ Bits
15. ICLR 2026Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
16. ICLR 2026From Neural Networks to Logical Theories: The Correspondence between Fibring Modal Logics and Fibring Neural Networks
17. ICLR 2026Geometric Constraints for Small Language Models to Understand and Expand Scientific Taxonomies
18. ICLR 2026HardcoreLogic: Challenging Large Reasoning Models with Long-tail Logic Puzzle Games
19. ICLR 2026Hot Fuzz: Temperature-Tunable Composition of Diffusion models with Fuzzy Logic
20. ICLR 2026Learning the Inverse Temperature of Ising Models under Hard Constraints using One Sample
21. ICLR 2026Light Differentiable Logic Gate Networks
22. ICLR 2026Near-Optimal Online Deployment and Routing for Streaming LLMs
23. ICLR 2026On the Expressiveness of State Space Models via Temporal Logics
24. ICLR 2026PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraints
25. ICLR 2026Probability Distributions Computed by Autoregressive Transformers
26. ICLR 2026Sharing State Between Prompts and Programs
27. ICLR 2026The Logical Expressiveness of Topological Neural Networks
28. ICLR 2026Towards Safe and Optimal Online Bidding: A Modular Look-ahead Lyapunov Framework
29. ICLR 2026Transformers are Inherently Succinct
30. ICML 2026A proximal ADMM for multiblock problems with block anti-upper triangular constraints
31. ICML 2026A Theory of Data Acquisition and Pricing at Scale
32. ICML 2026Abductive Reasoning with Probabilistic Commonsense
33. ICML 2026Align Forward, Adapt Backward: Closing the Discretization Gap in Logic Gate Networks
34. ICML 2026CAffNet: Hard Constraint-Affine Neural Networks
35. ICML 2026Capacitated Fair-Range Clustering: Hardness and Approximation Algorithms
36. ICML 2026DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers
37. ICML 2026Geometric Coherence Learning for Structuring Value Functions in Plain MDPs
38. ICML 2026HE-SNR: Uncovering Latent Logic via Entropy for Guiding Mid-Training on SWE-bench
39. ICML 2026KANFIS: A Neuro-Symbolic Framework for Interpretable and Uncertainty-Aware Learning
40. ICML 2026Learning Manifold and Itô Dynamics with Branched Neural Rough Differential Equations
41. ICML 2026Learning the Best Under Constraints: A Duality-Based Framework
42. ICML 2026Length Generalization Bounds for Transformers
43. ICML 2026Lifting Traces to Logic: Programmatic Skill Induction with Neuro-Symbolic Learning for Long-Horizon Agentic Tasks
44. ICML 2026Logical Guidance for the Exact Composition of Diffusion Models
45. ICML 2026Message Passing on the Edge: Towards Scalable and Expressive GNNs
46. ICML 2026Nash Equilibria in Games with Playerwise Concave Coupling Constraints: Existence and Computation
47. ICML 2026Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers
48. ICML 2026Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models
49. ICML 2026The Geometry of Projection Heads: Conditioning, Invariance, and Collapse
50. ICML 2026The Pareto-optimal Trade-off between Regret and Statistical Inference in Linear Stochastic Bandits under Safety Constraints

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。