Scholar
Hong Chen
Google Scholar ID: cZVeQVcAAAAJ
The Hong Kong University of Science and Technology (Guangzhou)
Large Language Models
Multi-modal LLMs
Efficient LLMs
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
43
H-index
3
i10-index
2
Publications
8
Co-authors
8
list available
Contact
Email
hchen763@connect.hkust-gz.edu.cn
CV
Open ↗
GitHub
Open ↗
Publications
9 items
SemTrace: Source-Grounded Semantic Signatures for Tracing LLM Exposure to Protected Documents
2026
Cited
0
TwinKV: A Composable Repair Pass for KV Cache Eviction via Pairwise Key Redundancy
2026
Cited
0
Seen, Said, or Forgotten? A Causal Audit of Visual KV Memory Across Dialog Turns
2026
Cited
0
Should Missing Modalities Always Be Necessary to Repair for Multi-modal Sentiment Analysis?
2026
Cited
0
Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs
2026
Cited
0
NestedKV: Nested Memory Routing for Long-Context KV Cache Compression
2026
Cited
0
OralGPT-Plus: Learning to Use Visual Tools via Reinforcement Learning for Panoramic X-ray Analysis
2026
Cited
0
SONIC: Segmented Optimized Nexus for Information Compression in Key-Value Caching
2026
Cited
0
Load more
Resume (English only)
Background
Research interests: Efficient inference of large language models, particularly in the area of KV Cache compression. Passionate about exploring the frontier of AI technology and making large models work in more scenarios.
Co-authors
8 total
Xiang Liu
HKUST(GZ)
Xuming Hu
Assistant Professor, HKUST(GZ) / HKUST
Wei Xia
Tencent
Yong Liu
Huawei, NTU, I2R
Xiuze Zhou
The Hong Kong University of Science and Technology (Guangzhou)
Xiaowen Chu
IEEE Fellow, Professor, Data Science and Analytics, HKUST(GZ)
Pengcheng WU
NTU, Deepir Inc, Gigle.AI
Lixin Zou
Wuhan University