HG
Hui Guan
cs.LGcs.AIcs.CVcs.DCcs.PFstat.MLcs.DBcs.IRcs.NEcs.SE
On Valency
published · living versionsW_rq7ubb8m·v1 · currentpublished
In-Place Zero-Space Memory Protection for CNN
with Lin Ning, Zhen Lin, Xipeng Shen, Huiyang Zhou +1
1 version
Preprints & journals
48 papers in the corpus · 2017–2026Transferable FB-GNN-MBE framework for potential energy surfaces: Data-adaptive transfer learning in deep learned many-body expansion theory.42775754 · Chen, Siqi, Wang, Zhiqiang, Shen, Yili et al.2026 · 0 citationsThe Journal of chemical physics. 2026;165(12)
Scout: Open-World Species Recognition on the Edge2609.22897v1 · Mohammad Mehdi Rastikerdar, Hui Guan, Deepak Ganesan2026 · 0 citationsarXiv
Kalypso: Relational LLM Serving2607.23815v2 · Hojae Son, Md Ashraful Islam, Huy Gia Cao et al.2026 · 0 citationsarXiv
Mosaic: Runtime-Efficient Multi-Agent Embodied Planning2607.09603v1 · Kunjal Panchal, Saayan Mitra, Sunav Choudhary et al.2026 · 0 citationsarXiv
EventADL: Open-Box Anomaly Detection and Localization Framework for Events in Cloud-Based Service Systems2605.00936v1 · Luan Pham, Victor Nicolet, Joey Dodds et al.2026 · 0 citationsarXiv
Interactive Clarification for Cloud Infrastructure-as-Code Synthesis2604.02382v2 · Zhenning Yang, Kaden Gruizenga, Tongyuan Miao et al.2026 · 0 citationsarXiv
Atom: Efficient On-Device Video-Language Pipelines Through Modular Reuse2512.17108v1 · Kunjal Panchal, Saayan Mitra, Somdeb Sarkhel et al.2025 · 0 citationsarXiv
Overcoming Extrapolation Challenges of Deep Learning by Incorporating Physics in Protein Sequence-Function Modeling.41293023 · Barethiya, Shrishti, Huang, Jian, Liu, Xiao et al.2026 · 2 citationsbioRxiv : the preprint server for biology. 2025
Automated Cloud Infrastructure-as-Code Reconciliation with AI Agents2510.20211v1 · Zhenning Yang, Hui Guan, Victor Nicolet et al.2025 · 0 citationsarXiv
HADIS: A Hybrid Architecture for Query-Aware Diffusion Model Serving2509.00642v3 · Qizheng Yang, Tung-I Chen, Siyu Zhao et al.2025 · 0 citationsarXiv
Adaptive Spiking with Plasticity for Energy Aware Neuromorphic Systems2508.11689v1 · Eduardo Calle-Ortiz, Hui Guan, Deepak Ganesan et al.2025 · 0 citationsarXiv
Memory Savings at What Cost? A Study of Alternatives to Backpropagation2506.21833v2 · Kunjal Panchal, Sunav Choudhary, Yuriy Brun et al.2025 · 0 citationsarXiv
Reimagining Parameter Space Exploration with Diffusion Models2506.17807v1 · Lijun Zhang, Xiao Liu, Hui Guan2025 · 0 citationsarXiv
ASTRA: Communication-Efficient Acceleration for Multi-Device Transformer Inference2505.19342v2 · Xiao Liu, Lijun Zhang, Deepak Ganesan et al.2025 · 0 citationsarXiv
Revolutionizing Spectroscopic Analysis Using Sequence-to-Sequence Models I: From Infrared Spectra to Molecular Structures10.26434/chemrxiv-2025-n4q84 · Ethan French, Xianqi Deng, Siqi Chen et al.2025 · 1 citationChemRxiv
AI-Driven Innovations in Volumetric Video Streaming: A Review2412.12208v1 · Erfan Entezami, Hui Guan2024 · 0 citationsarXiv
DiffServe: Efficiently Serving Text-to-Image Diffusion Models with Query-Aware Model Scaling2411.15381v2 · Sohaib Ahmad, Qizheng Yang, Haoliang Wang et al.2024 · 0 citationsarXiv
Aligned Vector Quantization for Edge-Cloud Collabrative Vision-Language Models2411.05961v2 · Xiao Liu, Lijun Zhang, Deepak Ganesan et al.2024 · 0 citationsarXiv
Integrating Graph Neural Networks and Many-Body Expansion Theory for Potential Energy Surfaces2411.01578v1 · Siqi Chen, Zhiqiang Wang, Xianqi Deng et al.2024 · 0 citationsarXiv
A Tree-Structured Multitask Model Architectures Recommendation System.37399156 · Zhang, Lijun, Liu, Xiao, Guan, Hui2024 · 1 citationIEEE transactions on neural networks and learning systems. 2024;35(11):15578-15588
Understanding and Alleviating Memory Consumption in RLHF for LLMs2410.15651v1 · Jin Zhou, Hanmei Yang, Steven (Jiaxun) Tang et al.2024 · 0 citationsarXiv
WildFit: Autonomous In-situ Model Adaptation for Resource-Constrained IoT Systems2409.07796v4 · Mohammad Mehdi Rastikerdar, Jin Huang, Hui Guan et al.2024 · 1 citationarXiv
AdapMTL: Adaptive Pruning Framework for Multitask Learning Model2408.03913v1 · Mingcan Xiang, Steven Jiaxun Tang, Qizheng Yang et al.2024 · 4 citationsarXiv
Loki: A System for Serving ML Inference Pipelines with Hardware and Accuracy Scaling2407.03583v1 · Sohaib Ahmad, Hui Guan, Ramesh K. Sitaraman2024 · 8 citationsarXiv
ProTrain: Efficient LLM Training via Memory-Aware Techniques2406.08334v2 · Hanmei Yang, Jin Zhou, Yao Fu et al.2024 · 1 citationarXiv
Graph Neural Network Training Systems: A Performance Comparison of Full-Graph and Mini-Batch2406.00552v4 · Saurabh Bajaj, Hojae Son, Juelin Liu et al.2024 · 15 citationsarXiv
Thinking Forward: Memory-Efficient Federated Finetuning of Language Models2405.15551v2 · Kunjal Panchal, Nisarg Parikh, Sunav Choudhary et al.2024 · 3 citationsarXiv
GraphMini: Accelerating Graph Pattern Matching Using Auxiliary Graphs2403.01050v1 · Juelin Liu, Sandeep Polisetty, Hui Guan et al.2024 · 2 citationsarXiv
Attack-Resilient Image Watermarking Using Stable Diffusion2401.04247v2 · Lijun Zhang, Xiao Liu, Antoni Viros Martin et al.2024 · 20 citationsarXiv
Efficient IoT Inference via Context-Awareness2310.19112v2 · Mohammad Mehdi Rastikerdar, Jin Huang, Shiwei Fang et al.2023 · 0 citationsarXiv
Attacking All Tasks at Once Using Adversarial Examples in Multi-Task Learning2305.12066v4 · Lijun Zhang, Xiao Liu, Kaleel Mahmood et al.2023 · 3 citationsarXiv
Structured Pruning for Multi-Task Deep Neural Networks2304.06840v1 · Siddhant Garg, Lijun Zhang, Hui Guan2023 · 3 citationsarXiv
GSplit: Scaling Graph Neural Network Training on Large Graphs via Split-Parallelism2303.13775v3 · Sandeep Polisetty, Juelin Liu, Kobi Falus et al.2023 · 2 citationsProceedings of the 8th Conference on Machine Learning and Systems (MLSys 2025)
Automatically Marginalized MCMC in Probabilistic Programming2302.00564v2 · Jinlin Lai, Javier Burroni, Hui Guan et al.2023 · 0 citationsarXiv
Flow: Per-Instance Personalized Federated Learning Through Dynamic Routing2211.15281v2 · Kunjal Panchal, Sunav Choudhary, Nisarg Parikh et al.2022 · 0 citationsarXiv
Uplifting Message Passing Neural Network with Graph Original Information2210.05382v2 · Xiao Liu, Lijun Zhang, Hui Guan2022 · 4 citationsarXiv
Improving Subgraph Representation Learning via Multi-View Augmentation2205.13038v3 · Yili Shen, Xiao Liu, Cheng-Wei Ju et al.2022 · 3 citationsarXiv
A Tree-Structured Multi-Task Model Recommender2203.05092v2 · Lijun Zhang, Xiao Liu, Hui Guan2022 · 1 citationarXiv
Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression2111.10320v1 · Yuezhou Sun, Wenlong Zhao, Lijun Zhang et al.2021 · 0 citationsarXiv
COMET: A Novel Memory-Efficient Deep Learning Training Framework by Using Error-Bounded Lossy Compression2111.09562v1 · Sian Jin, Chengming Zhang, Xintong Jiang et al.2021 · 3 citationsarXiv
AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning2110.13076v3 · Lijun Zhang, Xiao Liu, Hui Guan2021 · 11 citationsarXiv
Rethinking Hard-Parameter Sharing in Multi-Domain Learning2107.11359v3 · Lijun Zhang, Qizheng Yang, Xiao Liu et al.2021 · 24 citationsarXiv
Scalable Graph Neural Network Training: The Case for Sampling2105.02315v1 · Marco Serafini, Hui Guan2021 · 48 citationsACM SIGOPS Operating Systems Review, Volume 55, Issue 1, July 2021, pp 68-76
NumaPerf: Predictive and Full NUMA Profiling2102.05204v1 · Xin Zhao, Jin Zhou, Hui Guan et al.2021 · 0 citationsarXiv
SID-NISM: A Self-supervised Low-light Image Enhancement Framework2012.08707v1 · Lijun Zhang, Xiao Liu, Erik Learned-Miller et al.2020 · 4 citationsarXiv
Post-Training 4-bit Quantization on Embedding Tables1911.02079v1 · Hui Guan, Andrey Malevich, Jiyan Yang et al.2019 · 14 citationsarXiv
In-Place Zero-Space Memory Protection for CNN1910.14479v1 · Hui Guan, Lin Ning, Zhen Lin et al.2019 · 23 citationsarXivon Valency
First Study on Data Readiness Level1702.02107v1 · Hui Guan, Thanos Gentimis, Hamid Krim et al.2017 · 0 citationsarXiv
Career total: 92 works. 48 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.