可微推理论文趋势 2023–2026
可微逻辑
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 185 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 10 | 10 | 5 | 6 | 31 |
| 2024 | 5 | 8 | 6 | 10 | 29 |
| 2025 | 22 | 13 | 5 | 6 | 46 |
| 2026 | 28 | 16 | 14 | 21 | 79 |
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 22 篇，第 1 / 1 页
- NeurIPS 2025Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?
- NeurIPS 2025Consistency Conditions for Differentiable Surrogate Losses
- NeurIPS 2025Continuous Thought Machines
- NeurIPS 2025Curriculum Abductive Learning
- NeurIPS 2025Differentiable Decision Tree via "ReLU+Argmin" Reformulation
- NeurIPS 2025Differentiable Generalized Sliced Wasserstein Plans
- NeurIPS 2025Evaluating Program Semantics Reasoning with Type Inference in System $F$
- NeurIPS 2025HypoBootstrap: A Bootstrapping Framework for Inductive Reasoning
- NeurIPS 2025Improving Formal Reasoning of Transformer with State Stack
- NeurIPS 2025LinPrim: Linear Primitives for Differentiable Volumetric Rendering
- NeurIPS 2025Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models
- NeurIPS 2025Mind the Gap: Removing the Discretization Gap in Differentiable Logic Gate Networks
- NeurIPS 2025MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM
- NeurIPS 2025More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
- NeurIPS 2025MuSLR: Multimodal Symbolic Logical Reasoning
- NeurIPS 2025Optimal Minimum Width for the Universal Approximation of Continuously Differentiable Functions by Deep Narrow MLPs
- NeurIPS 2025Personalized Subgraph Federated Learning with Differentiable Auxiliary Projections
- NeurIPS 2025Reasoning Models Better Express Their Confidence
- NeurIPS 2025Reward Reasoning Models
- NeurIPS 2025Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI
- NeurIPS 2025Training Language Models to Reason Efficiently
- NeurIPS 2025VeriThinker: Learning to Verify Makes Reasoning Model Efficient
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查可微推理在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "differentiable-reasoning"}
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。