Yedi Hu, Yunzhi Yao, Ningyu Zhang, Shumin Deng, Huajun Chen (2024). Explore Model Kinship For Merging Large Language Models. EMNLP 2025 Findings.
About Me
I am currently a PhD candidate at Beijing Institute of Technology, working under the supervision of Prof. Yang Gao. My current research focuses on model merging, data synthesis, and interpretability for large language models.
Interests
- NLP
- LLMs
- Model Merging
- Interpretability
Education
- BSc in Artificial IntelligenceUniversity of Nottingham
- MSc in Artificial IntelligenceUniversity of Edinburgh
Papers
Technical Reports
Technical reports and collaborative research outputs I have contributed to.
AgentOmnia: Scaling Agentic Models for Full-Scenario Applications
AgentOmnia is a framework for scaling agentic models across consumer, business, and employee application scenarios, coordinating task-space definition, data synthesis, post-training, evaluation, and iterative improvement.
