鲁棒基准论文趋势 2023–2026

主要结论

• 鲁棒基准论文从 2023 年的 64 篇增长到 2026 年的 69 篇，三年间扩大到约 1.1 倍。
• NeurIPS 是发鲁棒基准论文最多的会议，2023–2026 年共 80 篇，占四个会议总量的 30%。
• 交叉方向里涨得最快的是通用机器学习 · evaluation：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 8 篇。
• 在「评测与基准」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的大模型基准是 154 倍，鲁棒基准是 1.1 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 2026Brittlebench: Quantifying LLM robustness via prompt sensitivity
• ICML 2026Geometrically Constrained Outlier Synthesis
• ICLR 2026Pitfalls in Evaluating Language Model Forecasters
• CVPR 2026FoV-Net Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Casting
• NeurIPS 2025Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations
• ICML 2025Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift
• ICLR 2025DRoP: Distributionally Robust Data Pruning
• CVPR 2025FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering
• NeurIPS 2024An Analysis of Robustness of Non-Lipschitz Networks
• ICML 2024Controllable Prompt Tuning For Balancing Group Distributional Robustness
• ICLR 2024Realistic Evaluation of Semi-supervised Learning Algorithms in Open Environments
• CVPR 2024A Bayesian Approach to OOD Robustness in Image Classification
• NeurIPS 2023Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations
• ICML 2023A Law of Robustness beyond Isoperimetry
• ICLR 2023A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification
• CVPR 2023Improving Robustness of Vision Transformers by Reducing Sensitivity To Patch Corruptions
• NeurIPS 2026Stress-Testing Neural Network Verifiers with Provably Robust Instances
• ICML 2026Optimal Attention Temperature Improves the Robustness of In-Context Learning under Distribution Shift in High Dimensions
• ICLR 2026CLARC: C/C++ Benchmark for Robust Code Search
• CVPR 2026LIBERO-Plus A Progressive Robustness Benchmark for Visual-Language-Action Models

全部鲁棒基准论文

共 264 篇，第 1 / 6 页

1. CVPR 2026Detecting Compressed AI-Generated Images via Phase Spectrum Robustness
2. CVPR 2026FoV-Net Rotation-Invariant CAD B-rep Learning via Field-of-View Ray Casting
3. CVPR 2026Geometry-driven OOD Detectors Are Class-Incremental Learners
4. CVPR 2026LIBERO-Plus A Progressive Robustness Benchmark for Visual-Language-Action Models
5. CVPR 2026Mitigating Error Amplification in Fast Adversarial Training
6. CVPR 2026On the Role of Temporal Granularity in the Robustness of
7. CVPR 2026PanoVGGT Feed-Forward 3D Reconstruction from Panoramic Imagery
8. CVPR 2026Scaling Test-Time Robustness of Vision-Language Models via Self-Critical Inference Framework
9. CVPR 2026Shedding Light on VLN Robustness A Black-box Framework for Indoor
10. CVPR 2026Towards Reliable Evaluation of Adversarial Robustness for Spiking Neural Networks
11. CVPR 2026Verifying Neural Network Robustness with Dual Perturbations
12. CVPR 2026WaTeRFlow Watermark Temporal Robustness via Flow Consistency
13. ICLR 2026CERTIFIED VS. EMPIRICAL ADVERSARIAL ROBUSTNESS VIA HYBRID CONVOLUTIONS WITH ATTENTION STOCHASTICITY
14. ICLR 2026CLARC: C/C++ Benchmark for Robust Code Search
15. ICLR 2026GneissWeb: Preparing High Quality Data for LLMs at Scale
16. ICLR 2026GraphUniverse: Enabling Systematic Evaluation of Inductive Generalization
17. ICLR 2026Is Your Paper Being Reviewed by an LLM? Benchmarking AI Text Detection in Peer Review
18. ICLR 2026Mapping Overlaps in Benchmarks through Perplexity in the Wild
19. ICLR 2026On the Bayes Inconsistency of Disagreement Discrepancy Surrogates
20. ICLR 2026ON THE ROLE OF IMPLICIT REGULARIZATION OF STOCHASTIC GRADIENT DESCENT IN GROUP ROBUSTNESS
21. ICLR 2026Pitfalls in Evaluating Language Model Forecasters
22. ICLR 2026PYRREGULAR: A Unified Framework for Irregular Time Series, with Classification Benchmarks
23. ICLR 2026QUEST: A robust attention formulation using query-modulated spherical attention
24. ICLR 2026SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
25. ICLR 2026The Price of Robustness: Stable Classifiers Need Overparameterization
26. ICLR 2026Training Dynamics Impact Post-Training Quantization Robustness
27. ICLR 2026When Flatness Does (Not) Guarantee Adversarial Robustness
28. ICML 2026A Geometry-Based View of Mahalanobis OOD Detection
29. ICML 2026AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition
30. ICML 2026AOEPT: Breaking the Implicit Modality-Reduction Bottleneck in Modality-Missing Prompt Tuning
31. ICML 2026Beyond Benchmarks: Toward Causally Faithful Evaluation of Large Language Models
32. ICML 2026CaliDist: Calibrating Large Language Models via Behavioral Robustness to Distraction
33. ICML 2026Correct Looks Better: Pairwise Comparisons Reveal Accuracy Rankings
34. ICML 2026Ellipsoidal Time Series Forecasting
35. ICML 2026Evaluating Robustness of Reasoning Models on Parameterized Logical Problems
36. ICML 2026Expanding the AI Evaluation Toolbox with Statistical Models
37. ICML 2026GENEB: Why Genomic Models Are Hard to Compare
38. ICML 2026Geometrically Constrained Outlier Synthesis
39. ICML 2026Improving the Robustness-Utility Trade-off in Decentralized Learning over Sparse Networks
40. ICML 2026Improving the Sensitivity of Backdoor Detectors via Class Subspace Orthogonalization
41. ICML 2026MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs
42. ICML 2026Non-Parametric Probabilistic Robustness: A Conservative Risk Estimator under Unknown Perturbation Distributions
43. ICML 2026Optimal Attention Temperature Improves the Robustness of In-Context Learning under Distribution Shift in High Dimensions
44. ICML 2026Posterior Mismatch Matters: Adversarial Training for Long-Tailed Robustness
45. ICML 2026ProMiSE: Protein Multi-State Evaluation Benchmark in Biological Contexts
46. ICML 2026RubricRobustness: Evaluating the Sensitivity of Rubrics-Based Benchmarks to Simple Perturbations
47. ICML 2026Self-Calibrated Consistency can Fight Back for Adversarial Robustness in Vision-Language Models
48. ICML 2026Towards Optimal Robustness in Learning-Augmented Paging
49. ICML 2026Training-Free Adversarial Robustness in Computational MRI
50. ICML 2026VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models

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。