Robustness

Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation CVPR 2024 Defog Artificial Intelligence Glasses: Neural Networks for the Imperfect Real World AAAI 2024 Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers NeurIPS 2024 Diffusion Models are Certifiably Robust Classifiers NeurIPS 2024 Discover and Mitigate Multiple Biased Subgroups in Image Classifiers CVPR 2024 Disentangling Linear Quadratic Control with Untrusted ML Predictions NeurIPS 2024 Distantly-Supervised Joint Extraction with Noise-Robust Learning ACL 2024 Distilling Robustness into Natural Language Inference Models with Domain-Targeted Augmentation ACL 2024 Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models EMNLP 2024 Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach NeurIPS 2024 Evaluating the Validity of Word-level Adversarial Attacks with Large Language Models ACL 2024 Exploiting Positional Bias for Query-Agnostic Generative Content in Search ACL 2024 “Flex Tape Can’t Fix That”: Bias and Misinformation in Edited Language Models EMNLP 2024 Fostering Trustworthiness in Machine Learning Algorithms AAAI 2024 Gradient-Guided Modality Decoupling for Missing-Modality Robustness AAAI 2024 Guaranteeing Robustness Against Real-World Perturbations In Time Series Classification Using Conformalized Randomized Smoothing UAI 2024 High-dimensional (Group) Adversarial Training in Linear Regression NeurIPS 2024 If You Want to Be Robust, Be Wary of Initialization NeurIPS 2024 ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object CVPR 2024 Impacts of Misspelled Queries on Translation and Product Search ACL 2024 Improving Subgroup Robustness via Data Selection NeurIPS 2024 Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models CVPR 2024 Investigating the Role of Instruction Variety and Task Difficulty in Robotic Manipulation Tasks EMNLP 2024 Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks EMNLP 2024 Learning Distributionally Robust Tractable Probabilistic Models in Continuous Domains UAI 2024