Peisong Wang
Scholar

Peisong Wang

Google Scholar ID: UYFZpk4AAAAJ
CASIA
Deep Neural Network Acceleration and Compression
Google Scholar↗
Citations & Impact
All-time
Citations
2,035
 
H-index
21
 
i10-index
32
 
Publications
20
 
Co-authors
4
list available
Contact
No contact links provided.
Publications
17 items
Astro: Activation-guided Structured Regularization for Outlier-Robust LLM Post-Training Quantization
2026
Cited
0
SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration
2026
Cited
0
DALI: A Workload-Aware Offloading Framework for Efficient MoE Inference on Local PCs
2026
Cited
0
Certain Head, Uncertain Tail: Expert-Sample for Test-Time Scaling in Fine-Grained MoE
2026
Cited
0
IntraSlice: Towards High-Performance Structural Pruning with Block-Intra PCA for LLMs
2026
Cited
0
CoTBox-TTT: Grounding Medical VQA with Visual Chain-of-Thought Boxes During Test-time Training
2025
Cited
0
Block Rotation is All You Need for MXFP4 Quantization
2025
Cited
0
DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization
2025
Cited
0
Resume (English only)
Co-authors
4 total
Qinghao Hu
Qinghao Hu
Institute of Automation, Chinese Academy of Sciences
Gang Li
Gang Li
Institute of Automation, Chinese Academy of Sciences
Co-author 3
Co-author 3
Chunjie Zhang
Chunjie Zhang
Beijing Jiaotong University