验证论文趋势 2023–2026

形式化与验证

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 111 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

验证论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202314128
20241047122
20251568433
2026191412348

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

全部验证论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 111 篇，第 2 / 3 页

  1. CVPR 2025Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zone
  2. CVPR 2025Training Data Provenance Verification: Did Your Model Use Synthetic Data from My Generative Model for Training?
  3. ICLR 2025Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification
  4. ICLR 2025Block Verification Accelerates Speculative Decoding
  5. ICLR 2025Data Taggants: Dataset Ownership Verification Via Harmless Targeted Data Poisoning
  6. ICLR 2025Rethinking and Improving Autoformalization: Towards a Faithful Metric and a Dependency Retrieval-based Approach
  7. ICLR 2025Sensitivity Verification for Additive Decision Tree Ensembles
  8. ICLR 2025Triples as the Key: Structuring Makes Decomposition and Verification Easier in LLM-based TableQA
  9. ICML 2025AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
  10. ICML 2025DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts
  11. ICML 2025No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural Networks
  12. ICML 2025PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification
  13. ICML 2025Position: Trustworthy AI Agents Require the Integration of Large Language Models and Formal Methods
  14. ICML 2025SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming
  15. ICML 2025Solving Probabilistic Verification Problems of Neural Networks using Branch and Bound
  16. ICML 2025Verification Learning: Make Unsupervised Neuro-Symbolic System Feasible
  17. NeurIPS 2025Characterizing the Expressivity of Fixed-Precision Transformer Language Models
  18. NeurIPS 2025Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification
  19. NeurIPS 2025Compositional Neural Network Verification via Assume-Guarantee Reasoning
  20. NeurIPS 2025DSCS: Fast CPDAG-Based Verification of Collapsible Submodels in High-Dimensional Bayesian Networks
  21. NeurIPS 2025Efficiently Verifiable Proofs of Data Attribution
  22. NeurIPS 2025Generating and Checking DNN Verification Proofs
  23. NeurIPS 2025Learning Simple Interpolants for Linear Integer Arithmetic
  24. NeurIPS 2025Let a Neural Network be Your Invariant
  25. NeurIPS 2025Limitations of Normalization in Attention
  26. NeurIPS 2025RvLLM: LLM Runtime Verification with Domain Knowledge
  27. NeurIPS 2025Self-Verification Provably Prevents Model Collapse in Recursive Synthetic Training
  28. NeurIPS 2025SpecEM: Training-Free LLM Ensembling via Iterative Drafting, Verification, and Online Feedback
  29. NeurIPS 2025Traversal Verification for Speculative Tree Decoding
  30. NeurIPS 2025Two‑Stage Learning of Stabilizing Neural Controllers via Zubov Sampling and Iterative Domain Expansion
  31. NeurIPS 2025Weaver: Shrinking the Generation-Verification Gap by Scaling Compute for Verification
  32. CVPR 2024Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation
  33. ICLR 2024CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
  34. ICLR 2024Expressivity of ReLU-Networks under Convex Relaxations
  35. ICLR 2024Lemur: Integrating Large Language Models in Automated Program Verification
  36. ICLR 2024Prediction without Preclusion: Recourse Verification with Reachable Sets
  37. ICML 2024Compact Optimality Verification for Optimization Proxies
  38. ICML 2024Copula-Nested Spectral Kernel Network
  39. ICML 2024Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification
  40. ICML 2024Relational DNN Verification With Cross Executional Bound Refinement
  41. ICML 2024SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks
  42. ICML 2024Verification of Machine Unlearning is Fragile
  43. ICML 2024VNN: Verification-Friendly Neural Networks with Hard Robustness Guarantees
  44. NeurIPS 2024Compact Proofs of Model Performance via Mechanistic Interpretability
  45. NeurIPS 2024Critically Assessing the State of the Art in Neural Network Verification
  46. NeurIPS 2024FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving
  47. NeurIPS 2024Neural Model Checking
  48. NeurIPS 2024Optimistic Verifiable Training by Controlling Hardware Nondeterminism
  49. NeurIPS 2024Relational Verification Leaps Forward with RABBit
  50. NeurIPS 2024Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes

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 查验证在 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": "verification"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇验证论文？
共 111 篇，按年份分别是 2023 年 8 篇、2024 年 22 篇、2025 年 33 篇、2026 年 48 篇。
NeurIPS 2026 有多少篇验证论文？
NeurIPS 2026 有 19 篇验证论文，上一届是 15 篇。
ICLR 2026 有多少篇验证论文？
ICLR 2026 有 14 篇验证论文，上一届是 6 篇。
ICML 2026 有多少篇验证论文？
ICML 2026 有 12 篇验证论文，上一届是 8 篇。
CVPR 2026 有多少篇验证论文？
CVPR 2026 有 3 篇验证论文，上一届是 4 篇。
哪个会议的验证论文最多？
NeurIPS，2023–2026 年共 45 篇。

「安全与可信」下的其他主题