Prati
Wenkai Yang
Naslov
Citirano
Citirano
Godina
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
W Yang, L Li, Z Zhang, X Ren, X Sun, B He
NAACL-HLT 2021, 2048–2058, 2021
1552021
Rethinking Stealthiness of Backdoor Attack against NLP Models
W Yang, Y Lin, P Li, J Zhou, X Sun
ACL-IJCNLP 2021 1, 5543–5557, 2021
1182021
RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models
W Yang, Y Lin, P Li, J Zhou, X Sun
EMNLP 2021, 2021
1082021
Towards Codable Watermarking for Injecting Multi-Bits Information to LLMs
L Wang*, W Yang*, D Chen*, H Zhou, Y Lin, F Meng, J Zhou, X Sun
ICLR 2024, 0
62*
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
W Yang, X Bi, Y Lin, S Chen, J Zhou, X Sun
NeurIPS 2024, 2024
332024
Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks
S Chen, W Yang, Z Zhang, X Bi, X Sun
Findings of EMNLP 2022, 2022
222022
Well-classified Examples are Underestimated in Classification with Deep Neural Networks
G Zhao, W Yang, X Ren, L Li, X Sun
AAAI 2022, 2021
192021
Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Features
S Chen, W Yang, X Bi, X Sun
Findings of EACL 2023, 2023
162023
Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter
Y Liu, X Bi, L Li, S Chen, W Yang, X Sun
Findings of ACL 2023, 2023
112023
Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization
W Yang, S Shen, G Shen, Y Wei, L Yong, Z Gong, Y Lin, JR Wen
ICLR 2025, 2024
92024
Exploring Backdoor Vulnerabilities of Chat Models
W Yang*, Y Hao*, Y Lin
COLING 2025, 2024
8*2024
Decentralized Decoupled Training for Federated Long-Tailed Learning
W Yang, D Chen, H Zhou, F Meng, J Zhou, X Sun
TMLR, 0
8*
Enabling Large Language Models to Learn from Rules
W Yang, Y Lin, J Zhou, J Wen
COLING 2025, 2023
42023
Understanding the Capabilities and Limitations of Weak-to-Strong Generalization
W Yao*, W Yang*, Z Wang, Y Lin, Y Liu
arXiv preprint arXiv:2502.01458, 2025
12025
Distilling Rule-based Knowledge into Large Language Models
W Yang, Y Lin, J Zhou, JR Wen
Proceedings of the 31st International Conference on Computational …, 2025
12025
Defying Forgetting in Continual Relation Extraction via Batch Spectral Norm Regularization
R Gao, W Yang, X Sun
2024 International Joint Conference on Neural Networks (IJCNN), 1-8, 2024
12024
When to Trust Aggregated Gradients: Addressing Negative Client Sampling in Federated Learning
W Yang, Y Lin, G Zhao, P Li, J Zhou, X Sun
Transactions on Machine Learning Research, 2023
12023
Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KL
W Yao, W Yang, Z Wang, Y Lin, Y Liu
arXiv preprint arXiv:2502.11107, 2025
2025
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–18