Scholar
Xin Zou
Google Scholar ID: z39tx_sAAAAJ
The Hong Kong University of Science and Technology (Guangzhou)
MLLMs
Multimodal Representation Learning
Machine Learning
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
291
H-index
10
i10-index
11
Publications
20
Co-authors
7
list available
Contact
No contact links provided.
Publications
10 items
Learning Disentangled Representations for Generalized Multi-view Clustering
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026
Cited
0
When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMs
2026
Cited
0
Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation
2026
Cited
0
Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval
2026
Cited
0
Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation
2026
Cited
0
Temporal Gains, Spatial Costs: Revisiting Video Fine-Tuning in Multimodal Large Language Models
2026
Cited
0
Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representations
2026
Cited
0
Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework
2026
Cited
0
Load more
Resume (English only)
Co-authors
7 total
Chang Tang
Senior Member of IEEE/CCF/CSIG, School of Software Engineering, HUST, Wuhan, China.
Xuming Hu
Assistant Professor, HKUST(GZ) / HKUST
Xinwang Liu
Senior Member of IEEE and CCF, NUDT
Linfeng Zhang (张林峰)
Shanghai Jiao Tong University
Chen Chen
Hong Kong University of Science and Technology; OPPO AI Center
Wanqing Li
Professor, University of Wollongong
Changqing Zhang
Professor, Tianjin University
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up