形式验证 ML论文趋势 2023–2026

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。

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 32 篇，第 1 / 1 页

1. NeurIPS 2026Certified but Private: Scalable Zero-Knowledge Proofs for the Formal Verification of Neural Networks
2. NeurIPS 2026End-to-End Verification of Neuro-symbolic Automata via Contrastive Logit-Gaps
3. NeurIPS 2026FACBench: A Benchmark for Formal-Anchor Collisions in Multilingual Mathematical Grounding
4. NeurIPS 2026FaithSieve: Fine-Grained Evaluation of Math Proofs with Faithful Formal Evidence
5. NeurIPS 2026FedTrace: Generated-Content-Based Watermark Verification for Traitor Tracing in Federated Learning
6. NeurIPS 2026FLARE: Verifying MILP Reformulations with LLM-Based Formal Proof Synthesis
7. NeurIPS 2026L$^2$EAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks
8. NeurIPS 2026Linear-time rule mining under formal guarantees
9. NeurIPS 2026SpecBridge: Learning Natural-Language Formalization Plans for the Formal Specification Synthesis Task
10. NeurIPS 2026Verification-Aware Training for Speculative Decoding
11. NeurIPS 2026VeriScope: Measuring Verification-Ready Verilog Artifacts
12. NeurIPS 2026VeruSAGE-Bench: A Benchmark Suite for Rust System Verification
13. NeurIPS 2025Bootstrapping Hierarchical Autoregressive Formal Reasoner with Chain-of-Proxy-Autoformalization
14. NeurIPS 2025Characterizing the Expressivity of Fixed-Precision Transformer Language Models
15. NeurIPS 2025DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products
16. NeurIPS 2025Efficiently Verifiable Proofs of Data Attribution
17. NeurIPS 2025Formal Models of Active Learning from Contrastive Examples
18. NeurIPS 2025Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks
19. NeurIPS 2025Learning Simple Interpolants for Linear Integer Arithmetic
20. NeurIPS 2025Let a Neural Network be Your Invariant
21. NeurIPS 2025SpecMAS: A Multi-Agent System for Self-Verifying System Generation via Formal Model Checking
22. NeurIPS 2025Traversal Verification for Speculative Tree Decoding
23. NeurIPS 2024Critically Assessing the State of the Art in Neural Network Verification
24. NeurIPS 2024FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving
25. NeurIPS 2024Neural Model Checking
26. NeurIPS 2024Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes
27. NeurIPS 2024The Expressive Capacity of State Space Models: A Formal Language Perspective
28. NeurIPS 2024The Power of Hard Attention Transformers on Data Sequences: A formal language theoretic perspective
29. NeurIPS 2024Verifiably Robust Conformal Prediction
30. NeurIPS 2024Verified Safe Reinforcement Learning for Neural Network Dynamic Models
31. NeurIPS 2023Compositional Policy Learning in Stochastic Control Systems with Formal Guarantees
32. NeurIPS 2023Provably Bounding Neural Network Preimages

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。