ZK
Zhenglun Kong
cs.LGcs.AIcs.CVcs.CLcs.ARcs.NEbioinformaticscs.GRcs.PFcs.RO
On Valency
published · living versionsW_sm7r6rxg·v1 · currentpublished
When Does Test-Time Search Help World Action Models? An Empirical Audit of Candidate Selection and Simulator Integrity
with Jun Liu, Dajie Sun, Zhenjiang Fan, Peiyan Dong +6
1 version
Preprints & journals
44 papers in the corpus · 2019–2026UniAR: A Unified Framework for Autism Recognition Enhanced by Multi-View Prompt Learning2609.31298v2 · Lei Xin, Zeheng Wang, Jiayin Zhu et al.2026 · 0 citationsarXiv
UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation Models2608.08627v2 · Lei Xin, Bin Gu, Peize Li et al.2026 · 0 citationsarXiv
An AI agent for treatment reasoning over a biomedical tool universe2606.28692v1 · Shanghua Gao, Ayush Noori, Richard Zhu et al.2026 · 0 citationsarXiv
When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making2603.16673v5 · Jun Liu, Pu Zhao, Zhenglun Kong et al.2026 · 0 citationsarXiv
Medea: An omics AI agent for therapeutic discovery.41648610 · Sui, Pengwei, Li, Michelle M, Gao, Shanghua et al.2026 · 7 citationsbioRxiv : the preprint server for biology. 2026
Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLA2512.22208v2 · Pu Zhao, Arash Akbari, Xuan Shen et al.2025 · 0 citationsarXiv
CONCERT predicts niche-aware perturbation responses in spatial transcriptomics.41292874 · Lin, Xiang, Kong, Zhenglun, Ghosh, Soumya et al.2025 · 4 citationsbioRxiv : the preprint server for biology. 2025
ToolUniverse: An open platform for democratizing AI scientists2509.23426v3 · Shanghua Gao, Richard Zhu, Pengwei Sui et al.2025 · 8 citationsarXiv
TSLA: A Task-Specific Learning Adaptation for Semantic Segmentation on Autonomous Vehicles Platform2508.12279v2 · Jun Liu, Zhenglun Kong, Pu Zhao et al.2025 · 3 citationsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 44, no. 4, pp. 1406-1419, April 2025
SPATIA: Multimodal Generation and Prediction of Spatial Cell Phenotypes2507.04704v3 · Zhenglun Kong, Mufan Qiu, John Boesen et al.2025 · 1 citationarXiv
Spatia: Multimodal Model for Prediction and Generation of Spatial Cell Phenotypes.40671942 · Kong, Zhenglun, Qiu, Mufan, Boesen, John et al.2026 · 0 citationsArXiv. 2025
Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration2506.05709v1 · Fanhu Zeng, Deli Yu, Zhenglun Kong et al.2025 · 0 citationsarXiv
ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning2505.21987v1 · Zhendong Mi, Zhenglun Kong, Geng Yuan et al.2025 · 0 citationsarXiv
Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation2505.23844v1 · Zhenglun Kong, Zheng Zhan, Shiyue Hou et al.2025 · 0 citationsarXiv
Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality2505.18227v4 · Zhenglun Kong, Yize Li, Fanhu Zeng et al.2025 · 1 citationarXiv
Structured Agent Distillation for Large Language Model2505.13820v5 · Jun Liu, Zhenglun Kong, Peiyan Dong et al.2025 · 0 citationsThe 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026)
TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools2503.10970v1 · Shanghua Gao, Richard Zhu, Zhenglun Kong et al.2025 · 19 citationsarXiv
RoRA: Efficient Fine-Tuning of LLM with Reliability Optimization for Rank Adaptation2501.04315v2 · Jun Liu, Zhenglun Kong, Peiyan Dong et al.2025 · 4 citationsarXiv
Artificial Intelligence for Central Dogma-Centric Multi-Omics: Challenges and Breakthroughs2412.12668v1 · Lei Xin, Caiyun Huang, Hao Li et al.2024 · 4 citationsarXiv
7B Fully Open Source Moxin-LLM/VLM -- From Pretraining to GRPO-based Reinforcement Learning Enhancement2412.06845v6 · Pu Zhao, Xuan Shen, Zhenglun Kong et al.2024 · 1 citationarXiv
Pruning Foundation Models for High Accuracy without Retraining2410.15567v1 · Pu Zhao, Fei Sun, Xuan Shen et al.2024 · 13 citationsarXiv
Rethinking Token Reduction for State Space Models2410.14725v1 · Zheng Zhan, Yushu Wu, Zhenglun Kong et al.2024 · 8 citationsarXiv
Exploring Token Pruning in Vision State Space Models2409.18962v1 · Zheng Zhan, Zhenglun Kong, Yifan Gong et al.2024 · 9 citationsarXiv
Search for Efficient Large Language Models2409.17372v2 · Xuan Shen, Pu Zhao, Yifan Gong et al.2024 · 7 citationsarXiv
Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers2407.18175v1 · Zhengang Li, Alec Lu, Yanyue Xie et al.2024 · 10 citationsarXiv
Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment2403.10799v6 · Jun Liu, Zhenglun Kong, Pu Zhao et al.2024 · 3 citationsarXiv
Squat: Quant Small Language Models on the Edge2402.10787v2 · Xuan Shen, Peiyan Dong, Zhenglun Kong et al.2024 · 5 citationsarXiv
Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge2312.05693v2 · Xuan Shen, Peiyan Dong, Lei Lu et al.2023 · 38 citationsarXiv
GPU Accelerated Color Correction and Frame Warping for Real-time Video Stitching2308.09209v1 · Lu Yang, Zhenglun Kong, Ting Li et al.2023 · 0 citationsarXiv
You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model2211.11152v2 · Shengkun Tang, Yaqing Wang, Zhenglun Kong et al.2022 · 37 citationsarXiv
Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training2211.10801v1 · Zhenglun Kong, Haoyu Ma, Geng Yuan et al.2022 · 15 citationsarXiv
HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers2211.08110v2 · Peiyan Dong, Mengshu Sun, Alec Lu et al.2022 · 127 citationsarXiv
Data Level Lottery Ticket Hypothesis for Vision Transformers2211.01484v3 · Xuan Shen, Zhenglun Kong, Minghai Qin et al.2022 · 6 citationsarXiv
Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training2209.11204v1 · Geng Yuan, Yanyu Li, Sheng Li et al.2022 · 6 citationsarXiv
SPViT: Enabling Faster Vision Transformers via Soft Token Pruning2112.13890v2 · Zhenglun Kong, Peiyan Dong, Xiaolong Ma et al.2021 · 29 citationsarXiv
MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge2110.14032v1 · Geng Yuan, Xiaolong Ma, Wei Niu et al.2021 · 52 citationsarXiv
Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization2110.10030v1 · Panjie Qi, Edwin Hsing-Mean Sha, Qingfeng Zhuge et al.2021 · 55 citationsarXiv
Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI2106.09166v2 · Geng Yuan, Zhiheng Liao, Xiaolong Ma et al.2021 · 38 citationsarXiv
A Compression-Compilation Framework for On-mobile Real-time BERT Applications2106.00526v2 · Wei Niu, Zhenglun Kong, Geng Yuan et al.2021 · 3 citationsarXiv
NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration2012.00596v3 · Zhengang Li, Geng Yuan, Wei Niu et al.2020 · 37 citationsarXiv
Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning2009.08065v4 · Bingbing Li, Zhenglun Kong, Tianyun Zhang et al.2020 · 39 citationsarXiv
Real-Time Execution of Large-scale Language Models on Mobile2009.06823v2 · Wei Niu, Zhenglun Kong, Geng Yuan et al.2020 · 10 citationsarXiv
SS-Auto: A Single-Shot, Automatic Structured Weight Pruning Framework of DNNs with Ultra-High Efficiency2001.08839v1 · Zhengang Li, Yifan Gong, Xiaolong Ma et al.2020 · 13 citationsarXiv
Automatic Tissue Image Segmentation Based on Image Processing and Deep Learning.30838122 · Kong, Zhenglun, Li, Ting, Luo, Junyi et al.2020 · 34 citationsJournal of healthcare engineering. 2019;2019:2912458
Career total: 69 works. 44 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.