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 47 篇，第 1 / 1 页

1. ICLR 2026$\boldsymbol{\partial^\infty}$-Grid: A Neural Differential Equation Solver with Differentiable Feature Grids
2. ICLR 2026Accelerated Learning with Linear Temporal Logic using Differentiable Simulation
3. ICLR 2026ActivationReasoning: Logical Reasoning in Latent Activation Spaces
4. ICLR 2026CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token Scheduling
5. ICLR 2026DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick
6. ICLR 2026Efficient Reasoning with Balanced Thinking
7. ICLR 2026Efficient Spatially-Variant Convolution via Differentiable Sparse Kernel Complex
8. ICLR 2026KaVa: Latent Reasoning via Compressed KV-Cache Distillation
9. ICLR 2026Learning to Reason via Mixture-of-Thought for Logical Reasoning
10. ICLR 2026Light Differentiable Logic Gate Networks
11. ICLR 2026NePTune: A Neuro-Pythonic Framework for Tunable Compositional Reasoning on Vision-Language
12. ICLR 2026Probability Distributions Computed by Autoregressive Transformers
13. ICLR 2026RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format
14. ICLR 2026RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling
15. ICLR 2026The Geometry of Reasoning: Flowing Logics in Representation Space
16. ICLR 2026Tversky Neural Networks: Psychologically Plausible Deep Learning with Differentiable Tversky Similarity
17. ICLR 2025Analytic DAG Constraints for Differentiable DAG Learning
18. ICLR 2025BlendRL: A Framework for Merging Symbolic and Neural Policy Learning
19. ICLR 2025Chemistry-Inspired Diffusion with Non-Differentiable Guidance
20. ICLR 2025Clique Number Estimation via Differentiable Functions of Adjacency Matrix Permutations
21. ICLR 2025Differentiable Causal Discovery for Latent Hierarchical Causal Models
22. ICLR 2025Differentiable Integer Linear Programming
23. ICLR 2025Differentiable Rule Induction from Raw Sequence Inputs
24. ICLR 2025DPaI: Differentiable Pruning at Initialization with Node-Path Balance Principle
25. ICLR 2025Generalizing Reasoning Problems to Longer Lengths
26. ICLR 2025Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation
27. ICLR 2025Linear Mode Connectivity in Differentiable Tree Ensembles
28. ICLR 2025PRDP: Progressively Refined Differentiable Physics
29. ICLR 2025ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
30. ICLR 2024COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits
31. ICLR 2024Differentiable Euler Characteristic Transforms for Shape Classification
32. ICLR 2024EBMDock: Neural Probabilistic Protein-Protein Docking via a Differentiable Energy Model
33. ICLR 2024Faithful Rule Extraction for Differentiable Rule Learning Models
34. ICLR 2024Generalized Neural Sorting Networks with Error-Free Differentiable Swap Functions
35. ICLR 2024Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs
36. ICLR 2024Logical Languages Accepted by Transformer Encoders with Hard Attention
37. ICLR 2024Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
38. ICLR 2023Can Neural Networks Learn Implicit Logic from Physical Reasoning?
39. ICLR 2023DFlow: Learning to Synthesize Better Optical Flow Datasets via a Differentiable Pipeline
40. ICLR 2023Improving Differentiable Neural Architecture Search by Encouraging Transferability
41. ICLR 2023Learning Group Importance using the Differentiable Hypergeometric Distribution
42. ICLR 2023Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
43. ICLR 2023Logical Entity Representation in Knowledge-Graphs for Differentiable Rule Learning
44. ICLR 2023Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient
45. ICLR 2023TILP: Differentiable Learning of Temporal Logical Rules on Knowledge Graphs
46. ICLR 2023VoGE: A Differentiable Volume Renderer using Gaussian Ellipsoids for Analysis-by-Synthesis
47. ICLR 2023Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic

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。