I received my Bachelor’s degree in Computer Science and Technology from Hebei University of Technology, China. Currently, under the guidance of Professor Yang liu, I am pursuing a master’s degree in next-generation electronic information technology at Xidian University. During my master’s studies, I focused on compositional zero-shot learning (CZSL), and have made several contributions to this area.
Currently, I am a first-year PhD student in Computer Science at the University of Illinois Chicago, advised by Professor Philip S. Yu. I am a member of the Big Data and Social Computing (BDSC) Lab. My research interests lie broadly in large language models (LLMs) and agentic AI, with a particular focus on agent memory. I am also broadly interested in topics such as agent reasoning, retrieval, learning, and long-term adaptation.
🔥 News
- 2026.03: 🎉🎉 Our work “Semi-Negative Contrastive Subclass Discriminative Network for Compositional Zero-Shot Learning” has been accepted.
- 2025.07: 🎉🎉 Our work “Multi-level Contextual Prototype Modulation for Compositional Zero-shot Learning” has been accepted.
- 2025.01: 🎉🎉 Our work “Concept-Aware Graph Convolutional Network for Compositional Zero-Shot Learning” has been accepted.
📝 Publications
Semi-Negative Contrastive Subclass Discriminative Network for Compositional Zero-Shot Learning
Yang Liu, Xinshuo Wang, Xinbo Gao, Jungong Han, Ling Shao
- We propose a Semi-Negative Contrastive Subclass Discriminative Network (SN-CSDN) based on contrastive learning.
Multi-level Contextual Prototype Modulation for Compositional Zero-shot Learning
Yang Liu, Xinshuo Wang, Xinbo Gao, Jungong Han, Ling Shao
- We propose Multilevel Contextual Prototype Modulation (MCPM), a transformerbased framework with a hierarchical structure that effectively integrates attributes and objects to generate richer visual embeddings.
Concept-Aware Graph Convolutional Network for Compositional Zero-Shot Learning
Yang Liu, Xinshuo Wang, Xinbo Gao, Jungong Han, Ling Shao
- We proposed a concept-aware graph convolutional network (GCN) that utilizes cross-attentions to extract features unique to attributes and objects from paired concept-sharing inputs.
🎖 Honors and Awards
- 2026 Outstanding Graduate Student.
- 2025 National Scholarship, First-Class School Scholarship.
- 2023 Scholarship for Freshmen, Outstanding Graduate, Third-Class School Scholarship.
- 2022 First-Class School Scholarship, Merit Student.
- 2021 First-Class School Scholarship, Merit Student, Encouragement Scholarship.
- 2020 Encouragement Scholarship, Third Prize of National Mathematics Competition, Excellent League Membe.
📖 Educations
- 2026.08 - present, computer science, University of Illinois Chicago.
- 2023.09 - 2026.06, New Generation Electronic Information Technology, School of Communication Engineering, Xidian University.
- 2019.09 - 2023.06, Computer Science and Technology, School of Artificial Intelligence and Data Science, Hebei University of Technology.