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 37 篇，第 1 / 1 页

1. CVPR 2026Goldilocks Test Sets for Face Verification
2. CVPR 2026Lipschitz Optimization for Formal Verification of Homographies
3. ICLR 2026Certifying the Full YOLO Pipeline: A Probabilistic Verification Approach
4. ICLR 2026Local Success Does Not Compose: Benchmarking Large Language Models for Compositional Formal Verification
5. ICLR 2026Out of the Shadows: Exploring a Latent Space for Neural Network Verification
6. ICLR 2026Overcoming Joint Intractability with Lossless Hierarchical Speculative Decoding
7. ICLR 2026Provably Explaining Neural Additive Models
8. ICLR 2026Softmax Transformers are Turing-Complete
9. ICLR 2026SpotIt: Evaluating Text-to-SQL Evaluation with Formal Verification
10. ICLR 2026The Counting Power of Transformers
11. ICLR 2026VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks
12. ICLR 2026VERIFY: A Novel Multi-Domain Dataset Grounding LTL in Contextual Natural Language via Provable Intermediate Logic
13. ICLR 2026VoG: Enhancing LLM Reasoning through Stepwise Verification on Knowledge Graphs
14. ICML 2026APE-Bench: Evaluating Automated Proof Engineering for Formal Math Libraries
15. ICML 2026Causally Evaluating the Learnability of Formal Language Tasks
16. ICML 2026CGRiC: Compositional Risk Certification for Structured LLM Outputs
17. ICML 2026Continuous Diffusion Models Can Obey Formal Syntax
18. ICML 2026Euclean: Automated Geometry Problem Formalization with Unified Verification in Lean
19. ICML 2026Formally Exploring Visual Anomaly Detection Evaluation Metrics
20. ICML 2026miniF2F-Dafny: LLM-Guided Mathematical Theorem Proving via Auto-Active Verification
21. ICML 2026Not All Invariants Are Equal: Curating Training Data to Accelerate Program Verification with SLMs
22. ICML 2026Probabilistic Robustness Certificates against Adversarial Attacks
23. ICML 2026Propose, Solve, Verify: Self-Play Through Formal Verification
24. ICML 2026Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
25. ICML 2026VIA-SD: Verification via Intra-Model Routing for Speculative Decoding
26. NeurIPS 2026Certified but Private: Scalable Zero-Knowledge Proofs for the Formal Verification of Neural Networks
27. NeurIPS 2026End-to-End Verification of Neuro-symbolic Automata via Contrastive Logit-Gaps
28. NeurIPS 2026FACBench: A Benchmark for Formal-Anchor Collisions in Multilingual Mathematical Grounding
29. NeurIPS 2026FaithSieve: Fine-Grained Evaluation of Math Proofs with Faithful Formal Evidence
30. NeurIPS 2026FedTrace: Generated-Content-Based Watermark Verification for Traitor Tracing in Federated Learning
31. NeurIPS 2026FLARE: Verifying MILP Reformulations with LLM-Based Formal Proof Synthesis
32. NeurIPS 2026L$^2$EAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks
33. NeurIPS 2026Linear-time rule mining under formal guarantees
34. NeurIPS 2026SpecBridge: Learning Natural-Language Formalization Plans for the Formal Specification Synthesis Task
35. NeurIPS 2026Verification-Aware Training for Speculative Decoding
36. NeurIPS 2026VeriScope: Measuring Verification-Ready Verilog Artifacts
37. NeurIPS 2026VeruSAGE-Bench: A Benchmark Suite for Rust System Verification

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。