Wenxiang Lin

Orcid: 0000-0001-5147-0844

According to our database1, Wenxiang Lin authored at least 12 papers between 2020 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert Swap.
CoRR, August, 2025

SP-MoE: Expediting Mixture-of-Experts Training with Optimized Pipelining Planning.
Proceedings of the IEEE INFOCOM 2025, 2025

ScheInfer: Efficient Inference of Large Language Models with Task Scheduling on Moderate GPUs.
Proceedings of the Euro-Par 2025: Parallel Processing, 2025

FSMoE: A Flexible and Scalable Training System for Sparse Mixture-of-Experts Models.
Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 2025

2024
Task Scheduling for Efficient Inference of Large Language Models on Single Moderate GPU Systems.
CoRR, 2024

Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated Schedules.
Proceedings of the IEEE INFOCOM 2024, 2024

2022
SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking.
Sensors, 2022

AFINet: Attentive Feature Integration Networks for image classification.
Neural Networks, 2022

2021
AFINet: Attentive Feature Integration Networks for Image Classification.
CoRR, 2021

ECascade-RCNN: Enhanced Cascade RCNN for Multi-scale Object Detection in UAV Images.
Proceedings of the 7th International Conference on Automation, Robotics and Applications, 2021

2020
LdsConv: Learned Depthwise Separable Convolutions by Group Pruning.
Sensors, 2020



  Loading...