Jailbreak and guard aligned language models with only few in-context demonstrations Z Wei, Y Wang, A Li, Y Mo, Y Wang
arXiv preprint arXiv:2310.06387; 📰 featured & scaled up by Anthropic at …, 2023
225 2023 Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap Y Wang*, Q Zhang*, Y Wang, J Yang, Z Lin
ICLR 2022, 2022
141 2022 Dissecting the diffusion process in linear graph convolutional networks Y Wang, Y Wang, J Yang, Z Lin
NeurIPS 2021, 2021
87 2021 How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders Q Zhang*, Y Wang*, Y Wang
NeurIPS 2022 Spotlight 🔦, 2022
77 2022 CFA: Class-wise Calibrated Fair Adversarial Training Z Wei, Y Wang, Y Guo, Y Wang
CVPR 2023, 2023
66 2023 When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture Y Mo, D Wu, Y Wang, Y Guo, Y Wang
NeurIPS 2022 Spotlight 🔦, 2022
65 2022 ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond X Guo*, Y Wang*, T Du*, Y Wang
ICLR 2023, 2023
45 2023 Optimization-induced graph implicit nonlinear diffusion Q Chen, Y Wang, Y Wang, J Yang, Z Lin
ICML 2022, 2022
42 2022 Residual relaxation for multi-view representation learning Y Wang, Z Geng, F Jiang, C Li, Y Wang, J Yang, Z Lin
NeurIPS 2021, 2021
40 2021 Do Generated Data Always Help Contrastive Learning? Y Wang*, J Zhang*, Y Wang
ICLR 2024, 2024
27 2024 Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning R Luo*, Y Wang*, Y Wang
ICLR 2023, 2023
27 2023 On the Generalization of Multi-modal Contrastive Learning Q Zhang*, Y Wang*, Y Wang
ICML 2023, 2023
25 2023 G M Li, X Guo, Y Wang, Y Wang, Z Lin
ICML 2022, 2022
24 2022 Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism Z Zhuo*, Y Wang*, J Ma, Y Wang
ICLR 2023, 2023
22 2023 Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding J Ma*, Y Wang*, Y Wang
NeurIPS 2023, 2023
19 2023 Adversarial examples are not real features A Li*, Y Wang*, Y Guo, Y Wang
NeurIPS 2023, 2023
18 2023 A Message Passing Perspective on Learning Dynamics of Contrastive Learning Y Wang*, Q Zhang*, T Du, J Yang, Z Lin, Y Wang
ICLR 2023, 2023
18 2023 A Theoretical Understanding of Self-Correction through In-context Alignment Y Wang*, Y Wu*, Z Wei, S Jegelka, Y Wang
NeurIPS 2024; 🏆 Best Paper Award at ICML'24 ICL Workshop, 2024
16 2024 Architecture matters: Uncovering implicit mechanisms in graph contrastive learning X Guo*, Y Wang*, Z Wei, Y Wang
NeurIPS 2023, 2023
16 2023 Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective Y Wang*, L Li*, J Yang, Z Lin, Y Wang
NeurIPS 2023, 2023
16 2023 
Yisen WangAssistant Professor, Peking UniversityПотвърден имейл адрес: pku.edu.cn
