Zeyu Qin

Orcid: 0000-0003-1733-7892

According to our database1, Zeyu Qin authored at least 25 papers between 2020 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
Reinforcement Learning with Rubric Anchors.
CoRR, August, 2025

Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models.
CoRR, June, 2025

Lifelong Safety Alignment for Language Models.
CoRR, May, 2025

Does Representation Intervention Really Identify Desired Concepts and Elicit Alignment?
CoRR, May, 2025

Scaling Laws of Synthetic Data for Language Models.
CoRR, March, 2025

Leveraging Reasoning with Guidelines to Elicit and Utilize Knowledge for Enhancing Safety Alignment.
CoRR, February, 2025

Preserving Diversity in Supervised Fine-Tuning of Large Language Models.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
Entropic Distribution Matching in Supervised Fine-tuning of LLMs: Less Overfitting and Better Diversity.
CoRR, 2024

MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning.
CoRR, 2024

Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping.
CoRR, 2024

Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

2023
Multi-Agent Reinforcement Learning Aided Computation Offloading in Aerial Computing for the Internet-of-Things.
IEEE Trans. Serv. Comput., 2023

Towards Stable Backdoor Purification through Feature Shift Tuning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Imitation Learning from Imperfection: Theoretical Justifications and Algorithms.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Revisiting Personalized Federated Learning: Robustness Against Backdoor Attacks.
Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023

Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

2022
A multidomain virtual network embedding algorithm based on multiobjective optimization for Internet of Drones architecture in Industry 4.0.
Softw. Pract. Exp., 2022

Adaptive Smoothness-weighted Adversarial Training for Multiple Perturbations with Its Stability Analysis.
CoRR, 2022

A multi-domain VNE algorithm based on multi-objective optimization for IoD architecture in Industry 4.0.
CoRR, 2022

Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021
Theoretical Study of Random Noise Defense against Query-Based Black-Box Attacks.
CoRR, 2021

Random Noise Defense Against Query-Based Black-Box Attacks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Collaborate Q-learning Aided Load Balance in Satellites Communications.
Proceedings of the 17th International Wireless Communications and Mobile Computing, 2021

A Line Selection Method Based on Transient Phase Current Variation Comparison.
Proceedings of the ICITEE 2021: The 4th International Conference on Information Technologies and Electrical Engineering, Changde, Hunan, China, October 29, 2021

2020
Traffic Optimization in Satellites Communications: A Multi-agent Reinforcement Learning Approach.
Proceedings of the 16th International Wireless Communications and Mobile Computing Conference, 2020


  Loading...