鲁棒基准论文趋势 2023–2026

分布外评测

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 264 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

鲁棒基准论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023122914964
2024161816959
2025341020872
20261815241269

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

全部鲁棒基准论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 264 篇，第 5 / 6 页

  1. CVPR 2023A Large-Scale Robustness Analysis of Video Action Recognition Models
  2. CVPR 2023Adversarial Robustness via Random Projection Filters
  3. CVPR 2023Benchmarking Robustness of 3D Object Detection to Common Corruptions
  4. CVPR 2023Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets
  5. CVPR 2023Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency
  6. CVPR 2023ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing
  7. CVPR 2023Improving Robustness of Vision Transformers by Reducing Sensitivity To Patch Corruptions
  8. CVPR 2023Revisiting Residual Networks for Adversarial Robustness
  9. CVPR 2023Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations
  10. ICLR 2023A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification
  11. ICLR 2023A Unified Algebraic Perspective on Lipschitz Neural Networks
  12. ICLR 2023Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts
  13. ICLR 2023Can CNNs Be More Robust Than Transformers?
  14. ICLR 2023Certified Training: Small Boxes are All You Need
  15. ICLR 2023Data augmentation alone can improve adversarial training
  16. ICLR 2023Distributionally Robust Post-hoc Classifiers under Prior Shifts
  17. ICLR 2023Diversify and Disambiguate: Out-of-Distribution Robustness via Disagreement
  18. ICLR 2023Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness
  19. ICLR 2023Feature Reconstruction From Outputs Can Mitigate Simplicity Bias in Neural Networks
  20. ICLR 2023Holistic Adversarially Robust Pruning
  21. ICLR 2023Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
  22. ICLR 2023Localized Randomized Smoothing for Collective Robustness Certification
  23. ICLR 2023Multi-lingual Evaluation of Code Generation Models
  24. ICLR 2023On Explaining Neural Network Robustness with Activation Path
  25. ICLR 2023On the Perils of Cascading Robust Classifiers
  26. ICLR 2023Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse
  27. ICLR 2023Prompting GPT-3 To Be Reliable
  28. ICLR 2023Provable Defense Against Geometric Transformations
  29. ICLR 2023Provable Robustness against Wasserstein Distribution Shifts via Input Randomization
  30. ICLR 2023Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play
  31. ICLR 2023Revisiting adapters with adversarial training
  32. ICLR 2023Robustness to corruption in pre-trained Bayesian neural networks
  33. ICLR 2023Sound Randomized Smoothing in Floating-Point Arithmetic
  34. ICLR 2023Squeeze Training for Adversarial Robustness
  35. ICLR 2023TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization
  36. ICLR 2023The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks
  37. ICLR 2023The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers
  38. ICLR 2023Towards Robustness Certification Against Universal Perturbations
  39. ICML 2023A Law of Robustness beyond Isoperimetry
  40. ICML 2023Adversarial robustness of amortized Bayesian inference
  41. ICML 2023BNN-DP: Robustness Certification of Bayesian Neural Networks via Dynamic Programming
  42. ICML 2023Do Perceptually Aligned Gradients Imply Robustness?
  43. ICML 2023Extending Kernel PCA through Dualization: Sparsity, Robustness and Fast Algorithms
  44. ICML 2023GraphCleaner: Detecting Mislabelled Samples in Popular Graph Learning Benchmarks
  45. ICML 2023How Many Perturbations Break This Model? Evaluating Robustness Beyond Adversarial Accuracy
  46. ICML 2023Improving Adversarial Robustness by Putting More Regularizations on Less Robust Samples
  47. ICML 2023Improving Adversarial Robustness of Deep Equilibrium Models with Explicit Regulations Along the Neural Dynamics
  48. ICML 2023Improving l1-Certified Robustness via Randomized Smoothing by Leveraging Box Constraints
  49. ICML 2023Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?
  50. ICML 2023Robustness in Multimodal Learning under Train-Test Modality Mismatch

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 查鲁棒基准在 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": "robustness-benchmarks"}

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鲁棒基准论文？
共 264 篇，按年份分别是 2023 年 64 篇、2024 年 59 篇、2025 年 72 篇、2026 年 69 篇。
NeurIPS 2026 有多少篇鲁棒基准论文？
NeurIPS 2026 有 18 篇鲁棒基准论文，上一届是 34 篇。
ICLR 2026 有多少篇鲁棒基准论文？
ICLR 2026 有 15 篇鲁棒基准论文，上一届是 10 篇。
ICML 2026 有多少篇鲁棒基准论文？
ICML 2026 有 24 篇鲁棒基准论文，上一届是 20 篇。
CVPR 2026 有多少篇鲁棒基准论文？
CVPR 2026 有 12 篇鲁棒基准论文，上一届是 8 篇。
哪个会议的鲁棒基准论文最多？
NeurIPS，2023–2026 年共 80 篇。

「评测与基准」下的其他主题