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 74 篇，第 1 / 2 页

  1. ICML 2026A Geometry-Based View of Mahalanobis OOD Detection
  2. ICML 2026AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition
  3. ICML 2026AOEPT: Breaking the Implicit Modality-Reduction Bottleneck in Modality-Missing Prompt Tuning
  4. ICML 2026Beyond Benchmarks: Toward Causally Faithful Evaluation of Large Language Models
  5. ICML 2026CaliDist: Calibrating Large Language Models via Behavioral Robustness to Distraction
  6. ICML 2026Correct Looks Better: Pairwise Comparisons Reveal Accuracy Rankings
  7. ICML 2026Ellipsoidal Time Series Forecasting
  8. ICML 2026Evaluating Robustness of Reasoning Models on Parameterized Logical Problems
  9. ICML 2026Expanding the AI Evaluation Toolbox with Statistical Models
  10. ICML 2026GENEB: Why Genomic Models Are Hard to Compare
  11. ICML 2026Geometrically Constrained Outlier Synthesis
  12. ICML 2026Improving the Robustness-Utility Trade-off in Decentralized Learning over Sparse Networks
  13. ICML 2026Improving the Sensitivity of Backdoor Detectors via Class Subspace Orthogonalization
  14. ICML 2026MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs
  15. ICML 2026Non-Parametric Probabilistic Robustness: A Conservative Risk Estimator under Unknown Perturbation Distributions
  16. ICML 2026Optimal Attention Temperature Improves the Robustness of In-Context Learning under Distribution Shift in High Dimensions
  17. ICML 2026Posterior Mismatch Matters: Adversarial Training for Long-Tailed Robustness
  18. ICML 2026ProMiSE: Protein Multi-State Evaluation Benchmark in Biological Contexts
  19. ICML 2026RubricRobustness: Evaluating the Sensitivity of Rubrics-Based Benchmarks to Simple Perturbations
  20. ICML 2026Self-Calibrated Consistency can Fight Back for Adversarial Robustness in Vision-Language Models
  21. ICML 2026Towards Optimal Robustness in Learning-Augmented Paging
  22. ICML 2026Training-Free Adversarial Robustness in Computational MRI
  23. ICML 2026VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models
  24. ICML 2026When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation
  25. ICML 2025Adversarial Robustness via Deformable Convolution with Stochasticity
  26. ICML 2025Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift
  27. ICML 2025Explaining the role of Intrinsic Dimensionality in Adversarial Training
  28. ICML 2025LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
  29. ICML 2025LEVIS: Large Exact Verifiable Input Spaces for Neural Networks
  30. ICML 2025Mahalanobis++: Improving OOD Detection via Feature Normalization
  31. ICML 2025Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation
  32. ICML 2025One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy
  33. ICML 2025Pixel-level Certified Explanations via Randomized Smoothing
  34. ICML 2025Position: AI Safety Must Embrace an Antifragile Perspective
  35. ICML 2025Position: AI Should Not Be An Imitation Game: Centaur Evaluations
  36. ICML 2025Position: Certified Robustness Does Not (Yet) Imply Model Security
  37. ICML 2025Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks
  38. ICML 2025Position: Medical Large Language Model Benchmarks Should Prioritize Construct Validity
  39. ICML 2025Position: Societal Impacts Research Requires Benchmarks for Creative Composition Tasks
  40. ICML 2025Probably Approximately Global Robustness Certification
  41. ICML 2025Quadratic Upper Bound for Boosting Robustness
  42. ICML 2025Statistical Hypothesis Testing for Auditing Robustness in Language Models
  43. ICML 2025Towards Robust Influence Functions with Flat Validation Minima
  44. ICML 2025When and How Does CLIP Enable Domain and Compositional Generalization?
  45. ICML 2024Can Implicit Bias Imply Adversarial Robustness?
  46. ICML 2024Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations
  47. ICML 2024Controllable Prompt Tuning For Balancing Group Distributional Robustness
  48. ICML 2024Density Ratio Estimation with Doubly Strong Robustness
  49. ICML 2024Enhancing Adversarial Robustness in SNNs with Sparse Gradients
  50. ICML 2024Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples

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