可微推理论文趋势 2023–2026

主要结论

• 可微推理论文从 2023 年的 31 篇增长到 2026 年的 79 篇，三年间扩大到约 2.5 倍。
• NeurIPS 是发可微推理论文最多的会议，2023–2026 年共 65 篇，占四个会议总量的 35%。
• 交叉方向里涨得最快的是数学推理：同时属于两个主题的论文从 2023 年的 3 篇增至 2026 年的 29 篇。
• 在「神经符号」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的数学推理是 10 倍，可微推理是 2.5 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 2026Beyond MSE: Differentiable Complexity Priors for Structure-Preserving Neural Denoising
• ICML 2026Differentiable Conformal Training for LLM Reasoning Factuality
• ICLR 2026$\boldsymbol{\partial^\infty}$-Grid: A Neural Differential Equation Solver with Differentiable Feature Grids
• CVPR 2026D-Convexity A Unified Differentiable Convex Shape Prior via Quasi-Concavity for
• NeurIPS 2025Consistency Conditions for Differentiable Surrogate Losses
• ICML 2025DiLQR: Differentiable Iterative Linear Quadratic Regulator via Implicit Differentiation
• ICLR 2025Analytic DAG Constraints for Differentiable DAG Learning
• CVPR 2025Differentiable Inverse Rendering with Interpretable Basis BRDFs
• NeurIPS 2024DeiSAM: Segment Anything with Deictic Prompting
• ICML 2024A Differentiable Partially Observable Generalized Linear Model with Forward-Backward Message Passing
• ICLR 2024Generalized Neural Sorting Networks with Error-Free Differentiable Swap Functions
• CVPR 2024Differentiable Display Photometric Stereo
• NeurIPS 2023Differentiable Clustering with Perturbed Spanning Forests
• ICML 2023End-to-end Differentiable Clustering with Associative Memories
• ICLR 2023Learning Group Importance using the Differentiable Hypergeometric Distribution
• CVPR 2023Deep Learning of Partial Graph Matching via Differentiable Top-K
• NeurIPS 2026Differentiable Exact Learning of Algorithms
• ICML 2026Hide&Seek: Learning to Explain in an End-to-End Differentiable Network
• ICLR 2026Tversky Neural Networks: Psychologically Plausible Deep Learning with Differentiable Tversky Similarity
• CVPR 2026DiffBMP Differentiable Rendering with Bitmap Primitives

全部可微推理论文

共 30 篇，第 1 / 1 页

1. ICML 2026Abductive Reasoning with Probabilistic Commonsense
2. ICML 2026AdaSplash-2: Faster Differentiable Sparse Attention
3. ICML 2026Align Forward, Adapt Backward: Closing the Discretization Gap in Logic Gate Networks
4. ICML 2026d$^2$p: Structured Soft Attention Is All You Need
5. ICML 2026Deterministic Differentiable Structured Pruning for Large Language Models
6. ICML 2026Differentiable Conformal Training for LLM Reasoning Factuality
7. ICML 2026Differentiable Weightless Controllers: Learning Logic Circuits for Continuous Control
8. ICML 2026Diffusion Differentiable Resampling
9. ICML 2026Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning
10. ICML 2026Hide&Seek: Learning to Explain in an End-to-End Differentiable Network
11. ICML 2026SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients
12. ICML 2026TT-Sparse: Learning Sparse Rule Models with Differentiable Truth Tables
13. ICML 2026TVDRNet: Text-driven Viewpoint Optimization via Differentiable Rendering for 3D Reasoning Segmentation
14. ICML 2026Two-Stage Unit Tying for Simplifying Differentiable Logic Gate Networks
15. ICML 2025Can Transformers Reason Logically? A Study in SAT Solving
16. ICML 2025Deliberation in Latent Space via Differentiable Cache Augmentation
17. ICML 2025Differentiable Structure Learning with Ancestral Constraints
18. ICML 2025DiLQR: Differentiable Iterative Linear Quadratic Regulator via Implicit Differentiation
19. ICML 2025DOLPHIN: A Programmable Framework for Scalable Neurosymbolic Learning
20. ICML 2024A Differentiable Partially Observable Generalized Linear Model with Forward-Backward Message Passing
21. ICML 2024Differentiable Combinatorial Scheduling at Scale
22. ICML 2024Differentiable Model Scaling using Differentiable Topk
23. ICML 2024Differentiable Weightless Neural Networks
24. ICML 2024Improving Neural Logic Machines via Failure Reflection
25. ICML 2024Scale-Free Image Keypoints Using Differentiable Persistent Homology
26. ICML 2023Differentiable Tree Operations Promote Compositional Generalization
27. ICML 2023End-to-end Differentiable Clustering with Associative Memories
28. ICML 2023Interpretable Neural-Symbolic Concept Reasoning
29. ICML 2023Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic
30. ICML 2023Neural Status Registers

常见问题

2023–2026 年四大会议一共有多少篇可微推理论文？

共 185 篇，按年份分别是 2023 年 31 篇、2024 年 29 篇、2025 年 46 篇、2026 年 79 篇。

NeurIPS 2026 有多少篇可微推理论文？

NeurIPS 2026 有 28 篇可微推理论文，上一届是 22 篇。

ICLR 2026 有多少篇可微推理论文？

ICLR 2026 有 16 篇可微推理论文，上一届是 13 篇。

ICML 2026 有多少篇可微推理论文？

ICML 2026 有 14 篇可微推理论文，上一届是 5 篇。

CVPR 2026 有多少篇可微推理论文？

CVPR 2026 有 21 篇可微推理论文，上一届是 6 篇。

哪个会议的可微推理论文最多？

NeurIPS，2023–2026 年共 65 篇。