Robustness Benchmarks papers, 2023–2026

Key findings

• Robustness Benchmarks went from 64 papers in 2023 to 69 in 2026, roughly 1.1x in three years.
• NeurIPS publishes the most Robustness Benchmarks work: 80 papers from 2023 to 2026, 30% of the four-venue total.
• The fastest-growing overlap is with General ML · evaluation: papers tagged with both rose from 0 in 2023 to 8 in 2026.
• Among the 5 topics under Evaluation and Benchmarks, it ranks #4 by 2026 paper count; the fastest grower in the group, LLM Benchmarks, is up 154x versus 1.1x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Robustness Benchmarks papers

72 papers, page 1 of 2

1. CVPR 2025Advancing Adversarial Robustness in GNeRFs: The IL2-NeRF Attack
2. CVPR 2025FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering
3. CVPR 2025Gain from Neighbors: Boosting Model Robustness in the Wild via Adversarial Perturbations Toward Neighboring Classes
4. CVPR 2025R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
5. CVPR 2025Rethinking the Adversarial Robustness of Multi-Exit Neural Networks in an Attack-Defense Game
6. CVPR 2025SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformers
7. CVPR 2025Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zone
8. CVPR 2025Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks
9. ICLR 2025Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddings
10. ICLR 2025Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness
11. ICLR 2025Consistency Checks for Language Model Forecasters
12. ICLR 2025Directional Gradient Projection for Robust Fine-Tuning of Foundation Models
13. ICLR 2025Do Large Language Models Truly Understand Geometric Structures?
14. ICLR 2025DRoP: Distributionally Robust Data Pruning
15. ICLR 2025In Search of Forgotten Domain Generalization
16. ICLR 2025MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures
17. ICLR 2025THE ROBUSTNESS OF DIFFERENTIABLE CAUSAL DISCOVERY IN MISSPECIFIED SCENARIOS
18. ICLR 2025Zero-cost Proxy for Adversarial Robustness Evaluation
19. ICML 2025Adversarial Robustness via Deformable Convolution with Stochasticity
20. ICML 2025Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift
21. ICML 2025Explaining the role of Intrinsic Dimensionality in Adversarial Training
22. ICML 2025LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
23. ICML 2025LEVIS: Large Exact Verifiable Input Spaces for Neural Networks
24. ICML 2025Mahalanobis++: Improving OOD Detection via Feature Normalization
25. ICML 2025Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation
26. ICML 2025One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy
27. ICML 2025Pixel-level Certified Explanations via Randomized Smoothing
28. ICML 2025Position: AI Safety Must Embrace an Antifragile Perspective
29. ICML 2025Position: AI Should Not Be An Imitation Game: Centaur Evaluations
30. ICML 2025Position: Certified Robustness Does Not (Yet) Imply Model Security
31. ICML 2025Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks
32. ICML 2025Position: Medical Large Language Model Benchmarks Should Prioritize Construct Validity
33. ICML 2025Position: Societal Impacts Research Requires Benchmarks for Creative Composition Tasks
34. ICML 2025Probably Approximately Global Robustness Certification
35. ICML 2025Quadratic Upper Bound for Boosting Robustness
36. ICML 2025Statistical Hypothesis Testing for Auditing Robustness in Language Models
37. ICML 2025Towards Robust Influence Functions with Flat Validation Minima
38. ICML 2025When and How Does CLIP Enable Domain and Compositional Generalization?
39. NeurIPS 2025A Technical Report on “Erasing the Invisible”: The 2024 NeurIPS Competition on Stress Testing Image Watermarks
40. NeurIPS 2025A Unified Approach to Submodular Maximization Under Noise
41. NeurIPS 2025Absence Bench: Language Models Can’t See What’s Missing
42. NeurIPS 2025Adaptive Distraction: Probing LLM Contextual Robustness with Automated Tree Search
43. NeurIPS 2025Adversarial Robustness of Nonparametric Regression
44. NeurIPS 2025Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations
45. NeurIPS 2025Augmenting Biological Fitness Prediction Benchmarks with Landscapes Features from GraphFLA
46. NeurIPS 2025Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent
47. NeurIPS 2025BenchmarkCards: Standardized Documentation for Large Language Model Benchmarks
48. NeurIPS 2025Bridging Crypto with ML-based Solvers: the SAT Formulation and Benchmarks
49. NeurIPS 2025Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations
50. NeurIPS 2025ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness

FAQ

How many Robustness Benchmarks papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

264 in total: 64 in 2023, 59 in 2024, 72 in 2025, 69 in 2026.

How many Robustness Benchmarks papers are at NeurIPS 2026?

NeurIPS 2026 has 18 Robustness Benchmarks papers, versus 34 the year before.

How many Robustness Benchmarks papers are at ICLR 2026?

ICLR 2026 has 15 Robustness Benchmarks papers, versus 10 the year before.

How many Robustness Benchmarks papers are at ICML 2026?

ICML 2026 has 24 Robustness Benchmarks papers, versus 20 the year before.

How many Robustness Benchmarks papers are at CVPR 2026?

CVPR 2026 has 12 Robustness Benchmarks papers, versus 8 the year before.

Which conference publishes the most Robustness Benchmarks papers?

NeurIPS, with 80 papers from 2023 to 2026.