Robustness

A Multi-modal Debiasing Model with Dynamical Constraint for Robust Visual Question Answering ACL 2023 Balanced Energy Regularization Loss for Out-of-Distribution Detection CVPR 2023 Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions NeurIPS 2023 Black-Box Adversarial Attack on Time Series Classification AAAI 2023 Byzantine-Tolerant Methods for Distributed Variational Inequalities NeurIPS 2023 Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning AAAI 2023 Characterizing the Optimal $0-1$ Loss for Multi-class Classification with a Test-time Attacker NeurIPS 2023 Combating Unknown Bias with Effective Bias-Conflicting Scoring and Gradient Alignment AAAI 2023 Conservative State Value Estimation for Offline Reinforcement Learning NeurIPS 2023 Controlling Learned Effects to Reduce Spurious Correlations in Text Classifiers ACL 2023 Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets CVPR 2023 Corruption-Robust Offline Reinforcement Learning with General Function Approximation NeurIPS 2023 Counterfactual Debiasing for Fact Verification ACL 2023 Cross-modal Active Complementary Learning with Self-refining Correspondence NeurIPS 2023 Defending Backdoor Attacks on Vision Transformer via Patch Processing AAAI 2023 Defending from Physically-Realizable Adversarial Attacks through Internal Over-Activation Analysis AAAI 2023 Degraded Polygons Raise Fundamental Questions of Neural Network Perception NeurIPS 2023 Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All? NeurIPS 2023 Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better ACL 2023 Detecting Argumentative Fallacies in the Wild: Problems and Limitations of Large Language Models EMNLP 2023 Drop Clause: Enhancing Performance, Robustness and Pattern Recognition Capabilities of the Tsetlin Machine AAAI 2023 Enhance Robustness of Machine Learning with Improved Efficiency AAAI 2023 Enhancing the Antidote: Improved Pointwise Certifications against Poisoning Attacks AAAI 2023 Explanation-based Finetuning Makes Models More Robust to Spurious Cues ACL 2023 Fast Bellman Updates for Wasserstein Distributionally Robust MDPs NeurIPS 2023