Inventor
WANG HONGSHENG
CN35 patents
⚠️ This page may combine multiple inventors who share the name “WANG HONGSHENG”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.
Zhejiang Lab
21 patentsUS11810366B1Nov 7, 2023
Joint modeling method and apparatus for enhancing local features of pedestrians
Zhejiang Lab36 citations94
US11699290B1Jul 11, 2023
Pedestrian re-identification method and apparatus based on local feature attention
Zhejiang Lab8 citations86
US11615247B1Mar 28, 2023
Labeling method and apparatus for named entity recognition of legal instrument
Zhejiang Lab9 citations85
US12039361B1Jul 16, 2024
Methods and apparatuses for executing tasks, storage mediums, and electronic devices
Zhejiang Lab3 citations75
US11934887B1Mar 19, 2024
Distributed model compilation
Zhejiang Lab2 citations73
US11805025B1Oct 31, 2023
Neural network computing-oriented modeling method and apparatus for distributed data routing
Zhejiang Lab5 citations72
US11714995B2Aug 1, 2023
Method for distributed type training adaptation and apparatus in deep learning framework and AI accelerator card
Zhejiang Lab5 citations72
US11341326B2May 24, 2022
Compression method and platform of pre-training language model based on knowledge distillation
Zhejiang Lab3 citations71
US11861505B2Jan 2, 2024
Method and apparatus of executing dynamic graph for neural network computation
Zhejiang Lab1 citations62
US11823053B2Nov 21, 2023
Method of neural network model computation-oriented intermediate representation by constructing physical computation graph, inferring information of input and output tensor edges of each node therein, performing memory optimization on tensor edges, and optimizing physical computation graph
Zhejiang Lab1 citations60
US12272177B2Apr 8, 2025
Method and apparatus for constructing three-dimensional data set of pedestrian re-identification based on neural radiation field
Zhejiang Lab0 citations52
US11941532B2Mar 26, 2024
Method for adapting deep learning framework to hardware device based on unified backend engine
Zhejiang Lab0 citations52
US11941507B2Mar 26, 2024
Data flow method and apparatus for neural network computation by determining input variables and output variables of nodes of a computational graph of a neural network
Zhejiang Lab0 citations52
US11915135B2Feb 27, 2024
Graph optimization method and apparatus for neural network computation
Zhejiang Lab0 citations52
US12468921B2Nov 11, 2025
Pipelining and parallelizing graph execution method for neural network model computation and apparatus thereof
Zhejiang Lab0 citations49
US11782723B1Oct 10, 2023
Intermediate representation method and apparatus for parallel execution of graph computation
Zhejiang Lab0 citations47
US11941514B2Mar 26, 2024
Method for execution of computational graph in neural network model and apparatus thereof
Zhejiang Lab0 citations45
US11669741B2Jun 6, 2023
Method and platform for meta-knowledge fine-tuning based on domain-invariant features
Zhejiang Lab0 citations44
US11354499B2Jun 7, 2022
Meta-knowledge fine tuning method and platform for multi-task language model
Zhejiang Lab0 citations44
US11526774B2Dec 13, 2022
Method for automatically compressing multitask-oriented pre-trained language model and platform thereof
Zhejiang Lab0 citations42
US11501171B2Nov 15, 2022
Method and platform for pre-trained language model automatic compression based on multilevel knowledge distillation
Zhejiang Lab0 citations38
ALPHION CORP
3 patentsUS8379301B2Feb 19, 2013
System and method for optical communication using polarization filtering
ALPHION CORP4 citations62
US7924498B2Apr 12, 2011
System and method for optical communication using polarization filtering
ALPHION CORP0 citations52
US7319555B2Jan 15, 2008
Integrated performance monitoring, performance maintenance, and failure detection for photonic regenerators
ALPHION CORP0 citations50