形式验证 ML论文趋势 2023–2026
验证辅助
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 84 篇被归入该主题的论文。
主要结论
- 形式验证 ML论文从 2023 年的 10 篇增长到 2026 年的 37 篇，三年间扩大到约 3.7 倍。
- NeurIPS 是发形式验证 ML论文最多的会议，2023–2026 年共 32 篇，占四个会议总量的 38%。
- 交叉方向里涨得最快的是推理模型：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 6 篇。
- 在「程序综合」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的定理证明是 13 倍，形式验证 ML是 3.7 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 2 | 5 | 2 | 1 | 10 |
| 2024 | 8 | 5 | 4 | 1 | 18 |
| 2025 | 10 | 5 | 3 | 1 | 19 |
| 2026 | 12 | 11 | 12 | 2 | 37 |
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 2026Certified but Private: Scalable Zero-Knowledge Proofs for the Formal Verification of Neural Networks
- ICML 2026Propose, Solve, Verify: Self-Play Through Formal Verification
- ICLR 2026Local Success Does Not Compose: Benchmarking Large Language Models for Compositional Formal Verification
- CVPR 2026Lipschitz Optimization for Formal Verification of Homographies
- NeurIPS 2025Formal Models of Active Learning from Contrastive Examples
- ICML 2025Position: Formal Mathematical Reasoning—A New Frontier in AI
- ICLR 2025Sensitivity Verification for Additive Decision Tree Ensembles
- CVPR 2025Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verification
- NeurIPS 2024Critically Assessing the State of the Art in Neural Network Verification
- ICML 2024Relational DNN Verification With Cross Executional Bound Refinement
- ICLR 2024CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
- CVPR 2024Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation
- NeurIPS 2023Provably Bounding Neural Network Preimages
- ICML 2023Trapdoor Normalization with Irreversible Ownership Verification
- ICLR 2023Fundamental Limits in Formal Verification of Message-Passing Neural Networks
- CVPR 2023Efficient Verification of Neural Networks Against LVM-Based Specifications
- NeurIPS 2026End-to-End Verification of Neuro-symbolic Automata via Contrastive Logit-Gaps
- ICML 2026Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
- ICLR 2026Out of the Shadows: Exploring a Latent Space for Neural Network Verification
- CVPR 2026Goldilocks Test Sets for Face Verification
全部形式验证 ML论文
共 21 篇，第 1 / 1 页
- ICML 2026APE-Bench: Evaluating Automated Proof Engineering for Formal Math Libraries
- ICML 2026Causally Evaluating the Learnability of Formal Language Tasks
- ICML 2026CGRiC: Compositional Risk Certification for Structured LLM Outputs
- ICML 2026Continuous Diffusion Models Can Obey Formal Syntax
- ICML 2026Euclean: Automated Geometry Problem Formalization with Unified Verification in Lean
- ICML 2026Formally Exploring Visual Anomaly Detection Evaluation Metrics
- ICML 2026miniF2F-Dafny: LLM-Guided Mathematical Theorem Proving via Auto-Active Verification
- ICML 2026Not All Invariants Are Equal: Curating Training Data to Accelerate Program Verification with SLMs
- ICML 2026Probabilistic Robustness Certificates against Adversarial Attacks
- ICML 2026Propose, Solve, Verify: Self-Play Through Formal Verification
- ICML 2026Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
- ICML 2026VIA-SD: Verification via Intra-Model Routing for Speculative Decoding
- ICML 2025PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification
- ICML 2025Position: Formal Mathematical Reasoning—A New Frontier in AI
- ICML 2025Verification Learning: Make Unsupervised Neuro-Symbolic System Feasible
- ICML 2024ED-Copilot: Reduce Emergency Department Wait Time with Language Model Diagnostic Assistance
- ICML 2024Relational DNN Verification With Cross Executional Bound Refinement
- ICML 2024Verification of Machine Unlearning is Fragile
- ICML 2024VNN: Verification-Friendly Neural Networks with Hard Robustness Guarantees
- ICML 2023Data-Copying in Generative Models: A Formal Framework
- ICML 2023Trapdoor Normalization with Irreversible Ownership Verification
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 查形式验证 ML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": "formal-verification-ml"}
常见问题
- 2023–2026 年四大会议一共有多少篇形式验证 ML论文？
- 共 84 篇，按年份分别是 2023 年 10 篇、2024 年 18 篇、2025 年 19 篇、2026 年 37 篇。
- NeurIPS 2026 有多少篇形式验证 ML论文？
- NeurIPS 2026 有 12 篇形式验证 ML论文，上一届是 10 篇。
- ICLR 2026 有多少篇形式验证 ML论文？
- ICLR 2026 有 11 篇形式验证 ML论文，上一届是 5 篇。
- ICML 2026 有多少篇形式验证 ML论文？
- ICML 2026 有 12 篇形式验证 ML论文，上一届是 3 篇。
- CVPR 2026 有多少篇形式验证 ML论文？
- CVPR 2026 有 2 篇形式验证 ML论文，上一届是 1 篇。
- 哪个会议的形式验证 ML论文最多？
- NeurIPS，2023–2026 年共 32 篇。