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 46 篇，第 1 / 1 页

1. CVPR 2025Differentiable Inverse Rendering with Interpretable Basis BRDFs
2. CVPR 2025Explainable Saliency: Articulating Reasoning with Contextual Prioritization
3. CVPR 2025LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models
4. CVPR 2025PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape Reconstruction
5. CVPR 2025Reasoning to Attend: Try to Understand How <SEG> Token Works
6. CVPR 2025Shape Abstraction via Marching Differentiable Support Functions
7. ICLR 2025Analytic DAG Constraints for Differentiable DAG Learning
8. ICLR 2025BlendRL: A Framework for Merging Symbolic and Neural Policy Learning
9. ICLR 2025Chemistry-Inspired Diffusion with Non-Differentiable Guidance
10. ICLR 2025Clique Number Estimation via Differentiable Functions of Adjacency Matrix Permutations
11. ICLR 2025Differentiable Causal Discovery for Latent Hierarchical Causal Models
12. ICLR 2025Differentiable Integer Linear Programming
13. ICLR 2025Differentiable Rule Induction from Raw Sequence Inputs
14. ICLR 2025DPaI: Differentiable Pruning at Initialization with Node-Path Balance Principle
15. ICLR 2025Generalizing Reasoning Problems to Longer Lengths
16. ICLR 2025Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation
17. ICLR 2025Linear Mode Connectivity in Differentiable Tree Ensembles
18. ICLR 2025PRDP: Progressively Refined Differentiable Physics
19. ICLR 2025ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
20. ICML 2025Can Transformers Reason Logically? A Study in SAT Solving
21. ICML 2025Deliberation in Latent Space via Differentiable Cache Augmentation
22. ICML 2025Differentiable Structure Learning with Ancestral Constraints
23. ICML 2025DiLQR: Differentiable Iterative Linear Quadratic Regulator via Implicit Differentiation
24. ICML 2025DOLPHIN: A Programmable Framework for Scalable Neurosymbolic Learning
25. NeurIPS 2025Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?
26. NeurIPS 2025Consistency Conditions for Differentiable Surrogate Losses
27. NeurIPS 2025Continuous Thought Machines
28. NeurIPS 2025Curriculum Abductive Learning
29. NeurIPS 2025Differentiable Decision Tree via "ReLU+Argmin" Reformulation
30. NeurIPS 2025Differentiable Generalized Sliced Wasserstein Plans
31. NeurIPS 2025Evaluating Program Semantics Reasoning with Type Inference in System $F$
32. NeurIPS 2025HypoBootstrap: A Bootstrapping Framework for Inductive Reasoning
33. NeurIPS 2025Improving Formal Reasoning of Transformer with State Stack
34. NeurIPS 2025LinPrim: Linear Primitives for Differentiable Volumetric Rendering
35. NeurIPS 2025Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models
36. NeurIPS 2025Mind the Gap: Removing the Discretization Gap in Differentiable Logic Gate Networks
37. NeurIPS 2025MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM
38. NeurIPS 2025More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
39. NeurIPS 2025MuSLR: Multimodal Symbolic Logical Reasoning
40. NeurIPS 2025Optimal Minimum Width for the Universal Approximation of Continuously Differentiable Functions by Deep Narrow MLPs
41. NeurIPS 2025Personalized Subgraph Federated Learning with Differentiable Auxiliary Projections
42. NeurIPS 2025Reasoning Models Better Express Their Confidence
43. NeurIPS 2025Reward Reasoning Models
44. NeurIPS 2025Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI
45. NeurIPS 2025Training Language Models to Reason Efficiently
46. NeurIPS 2025VeriThinker: Learning to Verify Makes Reasoning Model Efficient

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。