Zhonghua Jiang
Scholar

Zhonghua Jiang

Google Scholar ID: VsZaHKIAAAAJ
Zhejiang University
Multimodal LLMEfficient AI3D GenerationFederated Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
48
 
H-index
3
 
i10-index
2
 
Publications
5
 
Co-authors
2
list available
Contact
Emailjiangzhonghua@zju.edu.cnGitHubOpen ↗
Publications
7 items
SARe: Structure-Aware Large-Scale 3D Fragment Reassembly
2026
Cited
0
Beyond Student: An Asymmetric Network for Neural Network Inheritance
2026
Cited
0
AccKV: Towards Efficient Audio-Video LLMs Inference via Adaptive-Focusing and Cross-Calibration KV Cache Optimization
2025
Cited
0
PureKV: Plug-and-Play KV Cache Optimization with Spatial-Temporal Sparse Attention for Vision-Language Large Models
2025
Cited
0
FlowMM: Cross-Modal Information Flow Guided KV Cache Merging for Efficient Multimodal Context Inference
2025
Cited
0
TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting
2025
Cited
0
FedCFA: Alleviating Simpson's Paradox in Model Aggregation with Counterfactual Federated Learning
2024
Cited
0
Resume (English only)
Background
  • First-year PhD student (third-year of Master-PhD Continuous Program) in the College of Computer Science at Zhejiang University. Research interests include Efficient AI, MLLM, and LLM4HCI.
Miscellany
  • Conference Reviewer/Program Committee: ACM-MM 2024, ACM-MM 2025, MMAsia 2025, AAAI 2026.
Co-authors
2 total
Fei Wu
Fei Wu
Professor of Computer Science, Zhejiang University
Kun Kuang
Kun Kuang
Zhejiang University