Zhenglun Kong

Most-cited papers

SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning
Zhenglun Kong, Pei-Yan Dong, Xiao-Long Ma, Xin Meng +8 more
2021European Conference on Computer Vision258 citations
Semantic Scholar
HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers
Pei-Yan Dong, Meng-Shu Sun, Alec Lu, Yan-Yue Xie +7 more
2022International Symposium on High-Performance Computer Architecture153 citations Open access
Semantic Scholar
MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge
Geng Yuan, Xiao-Long Ma, Wei Niu, Zhen-Gang Li +12 more
2021Neural Information Processing Systems126 citations
Semantic Scholar
SPViT: Enabling Faster Vision Transformers via Soft Token Pruning
Zhenglun Kong, Pei-Yan Dong, Xiao-Long Ma, Xin Meng +6 more
2021arXiv.org97 citations
Semantic Scholar
Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge
Xuan Shen, Pei-Yan Dong, Lei Lu, Zhenglun Kong +4 more
2023AAAI Conference on Artificial Intelligence76 citations
Semantic Scholar
Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning
Bingbing Li, Zhenglun Kong, Tianyun Zhang, Ji Li +3 more
2020Findings70 citations Open access
Semantic Scholar
Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization
Panjie Qi, E. Sha, Q. Zhuge, Hongwu Peng +4 more
20212021 IEEE/ACM International Conference On Computer Aided Design (ICCAD)66 citations Open access
Semantic Scholar
You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model
Sheng Tang, Yaqing Wang, Zhenglun Kong, Tianchi Zhang +5 more
2022Computer Vision and Pattern Recognition64 citations Open access
Semantic Scholar
Automatic Tissue Image Segmentation Based on Image Processing and Deep Learning
Zhenglun Kong, Ting Li, Jun-Yi Luo, Shengpu Xu
2018BiOS39 citations Open access
Semantic Scholar
Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI
Geng Yuan, Zhiheng Liao, Xiao-Long Ma, Yuxuan Cai +10 more
2021IEEE International Symposium on Quality Electronic Design37 citations
Semantic Scholar
Pruning Foundation Models for High Accuracy without Retraining
Pu Zhao, Fei Sun, Xuan Shen, Pinrui Yu +3 more
2024Conference on Empirical Methods in Natural Language Processing36 citations
Semantic Scholar
Exploring Token Pruning in Vision State Space Models
Zheng Zhan, Zhenglun Kong, Yi-Fan Gong, Yu-Shu Wu +7 more
2024Neural Information Processing Systems35 citations
Semantic Scholar
Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training
Zhenglun Kong, Haoyu Ma, Geng Yuan, Meng-Shu Sun +11 more
2022AAAI Conference on Artificial Intelligence34 citations Open access
Semantic Scholar
NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration
Zhen-Gang Li, Geng Yuan, Wei Niu, Pu Zhao +12 more
2020Computer Vision and Pattern Recognition34 citations Open access
Semantic Scholar
Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment
Jun Liu, Zhenglun Kong, Pu Zhao, Chang-Di Yang +8 more
2024AAAI Conference on Artificial Intelligence28 citations Open access
Semantic Scholar
Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training
Geng Yuan, Yan-Yu Li, Sheng Li, Zhenglun Kong +4 more
2022Neural Information Processing Systems27 citations Open access
Semantic Scholar
Rethinking Token Reduction for State Space Models
Zheng Zhan, Yu-Shu Wu, Zhenglun Kong, Chang-Di Yang +5 more
2024Conference on Empirical Methods in Natural Language Processing25 citations
Semantic Scholar
Fast and Memory-Efficient Video Diffusion Using Streamlined Inference
Zheng Zhan, Yu-Shu Wu, Yi-Fan Gong, Zichong Meng +6 more
2024Neural Information Processing Systems24 citations
Semantic Scholar
Search for Efficient Large Language Models
Xuan Shen, Pu Zhao, Yi-Fan Gong, Zhenglun Kong +6 more
2024Neural Information Processing Systems23 citations
Semantic Scholar
SpeedDETR: Speed-aware Transformers for End-to-end Object Detection
Pei-Yan Dong, Zhenglun Kong, Xin Meng, P. Zhang +3 more
2023International Conference on Machine Learning22 citations
Semantic Scholar
RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
Jun Liu, Zhenglun Kong, Chang-Di Yang, Fan Yang +11 more
2025arXiv.org21 citations
Semantic Scholar
EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the Edge
Xuan Shen, Zhenglun Kong, Chang-Di Yang, Zhaoyang Han +10 more
2024arXiv.org21 citations
Semantic Scholar
Squat: Quant Small Language Models on the Edge
Xuan Shen, Pei-Yan Dong, Zhenglun Kong, Yi-Fan Gong +8 more
20242025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)20 citations Open access
Semantic Scholar
Sparse Learning for State Space Models on Mobile
Xuan Shen, Hang-Yu Zheng, Yi-Fan Gong, Zhenglun Kong +7 more
2025International Conference on Learning Representations19 citations
Semantic Scholar
SS-Auto: A Single-Shot, Automatic Structured Weight Pruning Framework of DNNs with Ultra-High Efficiency
Z. Li, Yifan Gong, Xiao-Long Ma, Si-Jia Liu +5 more
2020arXiv.org18 citations
Semantic Scholar
RoRA: Efficient Fine-Tuning of LLM with Reliability Optimization for Rank Adaptation
Jun Liu, Zhenglun Kong, Pei-Yan Dong, Chang-Di Yang +9 more
2025IEEE International Conference on Acoustics, Speech, and Signal Processing17 citations Open access
Semantic Scholar
HMC-TRAN: A Tensor-core Inspired Hierarchical Model Compression for Transformer-based DNNs on GPU
Shaoyi Huang, Shi-Yang Chen, Hongwu Peng, Daniel Manu +6 more
2021ACM Great Lakes Symposium on VLSI17 citations
Semantic Scholar
Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers
Zhen-Gang Li, Alec Lu, Yan-Yue Xie, Zhenglun Kong +8 more
2024International Conference on Supercomputing14 citations Open access
Semantic Scholar
Real-Time Execution of Large-scale Language Models on Mobile.
Wei Niu, Zhenglun Kong, Geng Yuan, Wei-Wen Jiang +6 more
202014 citations
Semantic Scholar
Structured Agent Distillation for Large Language Model Agents
Jun Liu, Zhenglun Kong, Pei-Yan Dong, Chang-Di Yang +12 more
2025Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems13 citations
Semantic Scholar
Artificial Intelligence for Central Dogma-Centric Multi-Omics: Challenges and Breakthroughs
Lei Xin, Caiyun Huang, Hao Li, S. Huang +7 more
202413 citations
Semantic Scholar
TSLA: A Task-Specific Learning Adaptation for Semantic Segmentation on Autonomous Vehicles Platform
Jun Liu, Zhenglun Kong, Pu Zhao, Weihao Zeng +8 more
2025IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems9 citations Open access
Semantic Scholar
Data Level Lottery Ticket Hypothesis for Vision Transformers
Xuan Shen, Zhenglun Kong, Minghai Qin, Pei-Yan Dong +5 more
2022International Joint Conference on Artificial Intelligence9 citations Open access
Semantic Scholar
Mutual Effort for Efficiency: A Similarity-based Token Pruning for Vision Transformers in Self-Supervised Learning
Sheng Li, Qi-Tao Tan, Yue-Zhen Dai, Zhenglun Kong +7 more
2025International Conference on Learning Representations8 citations
Semantic Scholar
AutoViT: Achieving Real-Time Vision Transformers on Mobile via Latency-aware Coarse-to-Fine Search
Zhenglun Kong, Dongkuan Xu, Zhen-Gang Li, Pei-Yan Dong +3 more
2025International Journal of Computer Vision7 citations Open access
Semantic Scholar
You Already Have It: A Generator-Free Low-Precision DNN Training Framework Using Stochastic Rounding
Geng Yuan, Sung-En Chang, Qing Jin, Alec Lu +10 more
2022European Conference on Computer Vision7 citations
Semantic Scholar
The Lottery Ticket Hypothesis for Vision Transformers
Xuan Shen, Zhenglun Kong, Minghai Qin, Pei-Yan Dong +5 more
2022arXiv.org7 citations Open access
Semantic Scholar
Achieving Real-Time Execution of Transformer-based Large-scale Models on Mobile with Compiler-aware Neural Architecture Optimization
Wei Niu, Zhenglun Kong, Geng Yuan, Wei-Wen Jiang +6 more
2020arXiv.org7 citations
Semantic Scholar
Q-TempFusion: Quantization-Aware Temporal Multi-Sensor Fusion on Bird's-Eye View Representation
Pinrui Yu, Zhenglun Kong, Pu Zhao, Pei-Yan Dong +4 more
2025IEEE Workshop/Winter Conference on Applications of Computer Vision6 citations
Semantic Scholar
Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLA
Pu Zhao, Xuan Shen, Zhenglun Kong, Yixin Shen +15 more
2025arXiv.org6 citations
Semantic Scholar
Condense: A Framework for Device and Frequency Adaptive Neural Network Models on the Edge
Yifan Gong, Pu Zhao, Zheng Zhan, Yu-Shu Wu +5 more
2023Design Automation Conference6 citations
Semantic Scholar
HotBEV: Hardware-oriented Transformer-based Multi-View 3D Detector for BEV Perception
Pei-Yan Dong, Zhenglun Kong, Xin Meng, Pinrui Yu +4 more
2023Neural Information Processing Systems6 citations
Semantic Scholar
HotaQ: Hardware Oriented Token Adaptive Quantization for Large Language Models
Xuan Shen, Zhaoyang Han, Lei Lu, Zhenglun Kong +8 more
2024IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems5 citations
Semantic Scholar
A Compression-Compilation Framework for On-mobile Real-time BERT Applications
Wei Niu, Zhenglun Kong, Geng Yuan, Wei-Wen Jiang +6 more
2021International Joint Conference on Artificial Intelligence5 citations Open access
Semantic Scholar
Automatical and accurate segmentation of cerebral tissues in fMRI dataset with combination of image processing and deep learning
Zhenglun Kong, Jun-Yi Luo, Shengpu Xu, Ting-Hung Li
2018BiOS5 citations
Semantic Scholar
When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making
Jun Liu, Pu Zhao, Zhenglun Kong, Xuan Shen +11 more
2026arXiv.org4 citations
Semantic Scholar
ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning
Zhen-Dong Mi, Zhenglun Kong, Geng Yuan, Shao-Yi Huang
2025arXiv.org4 citations
Semantic Scholar
7B Fully Open Source Moxin-LLM/VLM -- From Pretraining to GRPO-based Reinforcement Learning Enhancement
Pu Zhao, Xuan Shen, Zhenglun Kong, Yixin Shen +15 more
20244 citations
Semantic Scholar
Fully Open Source Moxin-7B Technical Report
Pu Zhao, Xuan Shen, Zhenglun Kong, Yixin Shen +12 more
2024arXiv.org4 citations
Semantic Scholar
UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation Models
Lei Xin, Bin Gu, Peize Li, Zi-Tong Wang +7 more
20263 citations
Semantic Scholar