Fuxun Yu

Orcid: 0000-0002-4880-6658

According to our database1, Fuxun Yu authored at least 60 papers between 2018 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
Online Learning via Memory: Retrieval-Augmented Detector Adaptation.
CoRR, 2024

LLM-dCache: Improving Tool-Augmented LLMs with GPT-Driven Localized Data Caching.
CoRR, 2024

Infinite-Dimensional Feature Interaction.
CoRR, 2024

QuadraNet V2: Efficient and Sustainable Training of High-Order Neural Networks with Quadratic Adaptation.
CoRR, 2024

Out-of-Distribution Detection via Deep Multi-Comprehension Ensemble.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

QuadraNet: Improving High-Order Neural Interaction Efficiency with Hardware-Aware Quadratic Neural Networks.
Proceedings of the 29th Asia and South Pacific Design Automation Conference, 2024

2023
LanCeX: A Versatile and Lightweight Defense Method against Condensed Adversarial Attacks in Image and Audio Recognition.
ACM Trans. Embed. Comput. Syst., 2023

Stable Diffusion For Aerial Object Detection.
CoRR, 2023

FedHC: A Scalable Federated Learning Framework for Heterogeneous and Resource-Constrained Clients.
CoRR, 2023

GACER: Granularity-Aware ConcurrEncy Regulation for Multi-Tenant Deep Learning.
CoRR, 2023

EagleRec: Edge-Scale Recommendation System Acceleration with Inter-Stage Parallelism Optimization on GPUs.
Proceedings of the 60th ACM/IEEE Design Automation Conference, 2023

2022
AntiDoteX: Attention-Based Dynamic Optimization for Neural Network Runtime Efficiency.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst., 2022

CaptorX: A Class-Adaptive Convolutional Neural Network Reconfiguration Framework.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst., 2022

A Survey of Multi-Tenant Deep Learning Inference on GPU.
CoRR, 2022

Powering Multi-Task Federated Learning with Competitive GPU Resource Sharing.
Proceedings of the Companion of The Web Conference 2022, Virtual Event / Lyon, France, April 25, 2022

SC-UDA: Style and Content Gaps aware Unsupervised Domain Adaptation for Object Detection.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022

FalCon: Fine-grained Feature Map Sparsity Computing with Decomposed Convolutions for Inference Optimization.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022

QuadraLib: A Performant Quadratic Neural Network Library for Architecture Optimization and Design Exploration.
Proceedings of the Fifth Conference on Machine Learning and Systems, 2022

Supporting Massive DLRM Inference through Software Defined Memory.
Proceedings of the 42nd IEEE International Conference on Distributed Computing Systems, 2022

Wideband Spectrum Sensing based on Collaborative Multi-Task Learning.
Proceedings of the 2022 IEEE International Conference on Communications Workshops, 2022

2021
REIN the RobuTS: Robust DNN-Based Image Recognition in Autonomous Driving Systems.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst., 2021

DiReCtX: Dynamic Resource-Aware CNN Reconfiguration Framework for Real-Time Mobile Applications.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst., 2021

A Survey of Large-Scale Deep Learning Serving System Optimization: Challenges and Opportunities.
CoRR, 2021

Supporting Massive DLRM Inference Through Software Defined Memory.
CoRR, 2021

Fed2: Feature-Aligned Federated Learning.
Proceedings of the KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2021

Automated Runtime-Aware Scheduling for Multi-Tenant DNN Inference on GPU.
Proceedings of the IEEE/ACM International Conference On Computer Aided Design, 2021

Helios: Heterogeneity-Aware Federated Learning with Dynamically Balanced Collaboration.
Proceedings of the 58th ACM/IEEE Design Automation Conference, 2021

2020
Third ArchEdge Workshop: Exploring the Design Space of Efficient Deep Neural Networks.
CoRR, 2020

Efficient Neural Network Implementation with Quadratic Neuron.
CoRR, 2020

Towards Latency-aware DNN Optimization with GPU Runtime Analysis and Tail Effect Elimination.
CoRR, 2020

Heterogeneous Federated Learning.
CoRR, 2020

Enabling efficient ReRAM-based neural network computing via crossbar structure adaptive optimization.
Proceedings of the ISLPED '20: ACM/IEEE International Symposium on Low Power Electronics and Design, 2020

Exploring the Design Space of Efficient Deep Neural Networks.
Proceedings of the 5th IEEE/ACM Symposium on Edge Computing, 2020

DC-CNN: Computational Flow Redefinition for Efficient CNN through Structural Decoupling.
Proceedings of the 2020 Design, Automation & Test in Europe Conference & Exhibition, 2020

AntiDote: Attention-based Dynamic Optimization for Neural Network Runtime Efficiency.
Proceedings of the 2020 Design, Automation & Test in Europe Conference & Exhibition, 2020

LanCe: A Comprehensive and Lightweight CNN Defense Methodology against Physical Adversarial Attacks on Embedded Multimedia Applications.
Proceedings of the 25th Asia and South Pacific Design Automation Conference, 2020

Tiny but Accurate: A Pruned, Quantized and Optimized Memristor Crossbar Framework for Ultra Efficient DNN Implementation.
Proceedings of the 25th Asia and South Pacific Design Automation Conference, 2020

2019
Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning.
CoRR, 2019

DoPa: A Fast and Comprehensive CNN Defense Methodology against Physical Adversarial Attacks.
CoRR, 2019

ADMM for Efficient Deep Learning with Global Convergence.
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019

Interpreting and Evaluating Neural Network Robustness.
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019

Task-adaptive incremental learning for intelligent edge devices.
Proceedings of the 4th ACM/IEEE Symposium on Edge Computing, 2019

MASKER: Adaptive Mobile Security Enhancement against Automatic Speech Recognition in Eavesdropping.
Proceedings of the 56th Annual Design Automation Conference 2019, 2019

ReForm: Static and Dynamic Resource-Aware DNN Reconfiguration Framework for Mobile Device.
Proceedings of the 56th Annual Design Automation Conference 2019, 2019

Functionality-Oriented Convolutional Filter Pruning.
Proceedings of the 30th British Machine Vision Conference 2019, 2019

REIN: a robust training method for enhancing generalization ability of neural networks in autonomous driving systems.
Proceedings of the 24th Asia and South Pacific Design Automation Conference, 2019

HAMPER: high-performance adaptive mobile security enhancement against malicious speech and image recognition.
Proceedings of the 24th Asia and South Pacific Design Automation Conference, 2019

CAPTOR: a class adaptive filter pruning framework for convolutional neural networks in mobile applications.
Proceedings of the 24th Asia and South Pacific Design Automation Conference, 2019

2018
How convolutional neural networks see the world - A survey of convolutional neural network visualization methods.
Math. Found. Comput., 2018

Distilling Critical Paths in Convolutional Neural Networks.
CoRR, 2018

Demystifying Neural Network Filter Pruning.
CoRR, 2018

Progressive Weight Pruning of Deep Neural Networks using ADMM.
CoRR, 2018

Interpretable Convolutional Filter Pruning.
CoRR, 2018

Interpreting Adversarial Robustness: A View from Decision Surface in Input Space.
CoRR, 2018

HASP: A High-Performance Adaptive Mobile Security Enhancement Against Malicious Speech Recognition.
CoRR, 2018

Towards Robust Training of Neural Networks by Regularizing Adversarial Gradients.
CoRR, 2018

How convolutional neural network see the world - A survey of convolutional neural network visualization methods.
CoRR, 2018

ASP: A Fast Adversarial Attack Example Generation Framework based on Adversarial Saliency Prediction.
CoRR, 2018

ReRise: An Adversarial Example Restoration System for Neuromorphic Computing Security.
Proceedings of the 2018 IEEE Computer Society Annual Symposium on VLSI, 2018

DiReCt: Resource-Aware Dynamic Model Reconfiguration for Convolutional Neural Network in Mobile Systems.
Proceedings of the International Symposium on Low Power Electronics and Design, 2018


  Loading...