Scholar
Yaoxin Yang
Google Scholar ID: -lZSGukAAAAJ
Fudan University
Efficient Deep Learning
MLLM
Model Compression
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
10
H-index
2
i10-index
0
Publications
3
Co-authors
2
list available
Publications
5 items
DecoMoE: Decoupling Visual Propagation and Expert Computation for Efficient Multimodal MoE Inference
2026
Cited
0
Revisiting Multimodal KV Cache Compression: A Frequency-Domain-Guided Outlier-KV-Aware Approach
2025
Cited
0
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
2025
Cited
0
TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models
2025
Cited
0
Multi-Level Decoupled Relational Distillation for Heterogeneous Architectures
2025
Cited
0
Co-authors
2 total
Chen Tao (陈涛)
Fudan University
Xudong Tan (谭旭东)
Fudan University
