Zhenglun Kong

Orcid: 0000-0002-8120-4456

According to our database¹, Zhenglun Kong authored at least 29 papers between 2017 and 2024.

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

2024

Efficient Pruning of Large Language Model with Adaptive Estimation Fusion.

[BibT_eX]

[DOI]

CoRR, 2024

EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the Edge.

[BibT_eX]

[DOI]

CoRR, 2024

Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

GPU Accelerated Color Correction and Frame Warping for Real-time Video Stitching.

[BibT_eX]

[DOI]

CoRR, 2023

HotBEV: Hardware-oriented Transformer-based Multi-View 3D Detector for BEV Perception.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Data Level Lottery Ticket Hypothesis for Vision Transformers.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023

SpeedDETR: Speed-aware Transformers for End-to-end Object Detection.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Fast and Fair Medical AI on the Edge Through Neural Architecture Search for Hybrid Vision Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE/ACM International Conference on Computer Aided Design, 2023

HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Symposium on High-Performance Computer Architecture, 2023

Late Breaking Results: Fast Fair Medical Applications? Hybrid Vision Models Achieve the Fairness on the Edge.

[BibT_eX]

[DOI]

Proceedings of the 60th ACM/IEEE Design Automation Conference, 2023

Condense: A Framework for Device and Frequency Adaptive Neural Network Models on the Edge.

[BibT_eX]

[DOI]

Proceedings of the 60th ACM/IEEE Design Automation Conference, 2023

You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022

The Lottery Ticket Hypothesis for Vision Transformers.

[BibT_eX]

[DOI]

CoRR, 2022

Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

You Already Have It: A Generator-Free Low-Precision DNN Training Framework Using Stochastic Rounding.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

2021

SPViT: Enabling Faster Vision Transformers via Soft Token Pruning.

[BibT_eX]

[DOI]

CoRR, 2021

MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI.

[BibT_eX]

[DOI]

Proceedings of the 22nd International Symposium on Quality Electronic Design, 2021

A Compression-Compilation Framework for On-mobile Real-time BERT Applications.

[BibT_eX]

[DOI]

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021

Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization.

[BibT_eX]

[DOI]

Proceedings of the IEEE/ACM International Conference On Computer Aided Design, 2021

HMC-TRAN: A Tensor-core Inspired Hierarchical Model Compression for Transformer-based DNNs on GPU.

[BibT_eX]

[DOI]

Proceedings of the GLSVLSI '21: Great Lakes Symposium on VLSI 2021, 2021

NPAS: A Compiler-Aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

2020

6.7ms on Mobile with over 78% ImageNet Accuracy: Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration.

[BibT_eX]

[DOI]

CoRR, 2020

Achieving Real-Time Execution of Transformer-based Large-scale Models on Mobile with Compiler-aware Neural Architecture Optimization.

[BibT_eX]

[DOI]

CoRR, 2020

SS-Auto: A Single-Shot, Automatic Structured Weight Pruning Framework of DNNs with Ultra-High Efficiency.

[BibT_eX]

[DOI]

CoRR, 2020

Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2020, 2020

2017

High stability and robustness of a developed novel laser acupuncture theranostic device.

[BibT_eX]

[DOI]

Microelectron. Reliab., 2017

Zhenglun Kong

Timeline

Legend:

Links

On csauthors.net:

Bibliography

Loading...