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 84 篇，第 1 / 2 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
38. CVPR 2025Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verification
39. ICLR 2025A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language
40. ICLR 2025Block Verification Accelerates Speculative Decoding
41. ICLR 2025Sensitivity Verification for Additive Decision Tree Ensembles
42. ICLR 2025Training Neural Networks as Recognizers of Formal Languages
43. ICLR 2025Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues
44. ICML 2025PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification
45. ICML 2025Position: Formal Mathematical Reasoning—A New Frontier in AI
46. ICML 2025Verification Learning: Make Unsupervised Neuro-Symbolic System Feasible
47. NeurIPS 2025Bootstrapping Hierarchical Autoregressive Formal Reasoner with Chain-of-Proxy-Autoformalization
48. NeurIPS 2025Characterizing the Expressivity of Fixed-Precision Transformer Language Models
49. NeurIPS 2025DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products
50. NeurIPS 2025Efficiently Verifiable Proofs of Data Attribution

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。