Profiles2020-2026
Yang Zhou
Auburn University
20Papers
3Last author
26Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers20
- Automatic Dialectic Jailbreak: A Framework for Generating Effective Jailbreak StrategiesAuthor 2 of 7ICLR 2026
- Generalizing Linear Autoencoder Recommenders with Decoupled Expected Quadratic LossAuthor 4 of 5ICLR 2026
- Mitigating the Modality Gap in Vision–Language Models with Fractal Spectral GeometryAuthor 2 of 5ICML 2026
- Structured Multi-step Jailbreaking under a Hamiltonian Generative FormulationAuthor 2 of 8ICML 2026
- Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial RobustnessAuthor 6 of 6NeurIPS 2025 · 12 citations
- PAC-Bayes Bounds for Multivariate Linear Regression and Linear AutoencodersAuthor 4 of 4NeurIPS 2025 · 3 citations
- Effective Federated Graph MatchingAuthor 1 of 5ICML 2024 · 1 citation
- Fast Federated Machine Unlearning with Nonlinear Functional TheoryAuthor 2 of 8ICML 2023 · 77 citations
- Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive OptimizationAuthor 3 of 8EMNLP 2023 · 43 citations
- Dimension-independent Certified Neural Network Watermarks via Mollifier SmoothingAuthor 2 of 5ICML 2023 · 10 citations
- Accelerated Federated Learning with Decoupled Adaptive OptimizationAuthor 3 of 6ICML 2022 · 62 citations
- Prompt Certified Machine Unlearning with Randomized Gradient Smoothing and QuantizationAuthor 2 of 5NeurIPS 2022 · 56 citations
- Input-agnostic Certified Group Fairness via Gaussian Parameter SmoothingAuthor 3 of 4ICML 2022 · 18 citations
- Validating the Lottery Ticket Hypothesis with Inertial Manifold TheoryAuthor 4 of 10NeurIPS 2021 · 45 citations
- Expressive 1-Lipschitz Neural Networks for Robust Multiple Graph Learning against Adversarial AttacksAuthor 6 of 9ICML 2021 · 33 citations
- Towards a Better Understanding of Linear Models for RecommendationAuthor 6 of 6KDD 2021 · 21 citations
- Integrated Defense for Resilient Graph MatchingAuthor 6 of 10ICML 2021 · 15 citations
- Adversarial Attack against Cross-lingual Knowledge Graph AlignmentAuthor 3 of 9EMNLP 2021 · 10 citations
- Diverse and Informative Dialogue Generation with Context-Specific Commonsense Knowledge AwarenessAuthor 4 of 5ACL 2020 · 104 citations
- Adversarial Attacks on Deep Graph MatchingAuthor 3 of 6NeurIPS 2020 · 42 citations
