Zejian Xie
Orcid: 0009-0003-2967-0526
According to our database1,
Zejian Xie authored at least 9 papers
between 2023 and 2026.
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2026
CoRLHF: Reinforcement learning from human feedback with cooperative policy-reward optimization for LLMs.
Expert Syst. Appl., 2026
2025
CoRR, September, 2025
CoRR, March, 2025
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
2024
2023
Never Lost in the Middle: Improving Large Language Models via Attention Strengthening Question Answering.
CoRR, 2023