Principal Research Manager
Microsoft
Email: fuxunyu at microsoft dot com
[06/2025] Team wins Top-1 in EarthVision Embed2Scale Geo-Embedding Challenge in CVPR'25 (Link)!
[09/2024] One collaborative work on High-order Neural Network Design is accepted in NeurIPS'24!
[09/2024] One collaborative work on Federated Learning is accepted in ACSAC'24!
[08/2024] One collaborative work on LLM-inspired Retrieval-Augmented Detector Adaptaton is accepted in ECCV'24 HCV Workshop!
[05/2024] One collaborative work on Out-of-Distribution Detection is accepted in ICML'24!
[11/2023] One collaborative work on the High-Order Neural Network Design received the Best Paper Award Nomination in ASP-DAC'24!
[09/2022] One collaborative work on Multi-Tenant Federated Learning received the Best Paper Award in MLSys CrossFL Workshop'22 (Link)!
[05/2022] One collaborative work on Quadratic Neural Networks received the Outstanding Paper Award in MLSys'22 (Top 5 paper, Link)!
[04/2022] I received the Outstanding Academic Achievement Award 2022 of GMU Volgenau School of Engineering (Link)!
[04/2022] One work on memory optimization for recommendation model (during Facebook Internship) is accepted in ICDCS'22 !
[04/2022] Our work on GPU-aware DNN design (poster) is accepted in EuroSys'22 !
[07/2021] Our work on multi-tenant DNN scheduling on GPUs is accepted in ICCAD'21 !
[05/2021] Our work on feature-aligned federated learning (Fed^2) is accepted in KDD'21 !
[02/2021] I will intern at Facebook (Infrastructure Team, Capacity Engineering & Analysis) in summer, 2021 !
[11/2020] One project (Privacy-preserving FL with personal mobility data) won the first prize in IEEE Services Hackathon 2020 [link] !
[04/2020] Our work ''Antidote'' on dynamic feature pruning receives the Best Paper Award Nomination in DATE'20 !
[01/2020] I will intern at Microsoft Research (Redmond) under the supervision of Dr. Di Wang in summer, 2020 !
[05/2019] Our work "Interpreting and Evaluating Adversarial Robustness" is accepted in IJCAI'19 !
[03/2019] I will intern at Microsoft Research (Redmond) under the supervision of Dr. Di Wang in summer, 2019 !
[03/2019] One work on Gradient-Free DNN Training using ADMM by Junxiang and me is accepted in KDD'19 !
Cross-Modality Vision Language Modeling
VLM Finetuning and Reinforcement Learning
Auto-Regressive Modeling for Graphs
Agentic AI Workflow Development
Retrieval-Augmented Learning and Adaptation
Stable Diffusion for Downstream CV Task
Full-Stack Optimization on GPUs ( Algorithm/Compiler/Runtime )
Recommendation model memory system optimization
DNN Security and Adversarial Robustness
DNN Interpretability and Explainability
[CVPR-E2S'25] Z Xu, R Tang, M Bianco, Q Zhang, R Madhok, N Karianakis, F Yu, 404 Embedding Not Found: Top-1 Winning Solution on EarthVision Embed2Scale Challenge (CVPR 2025), in EarthVision Embed2Scale Challenge, CVPR, 2025.
[WACV'25] R Kukal, J Patravali, F Yu, S Singh, N Karianakis, R Madhok. Click & Describe: Multimodal Grounding and Tracking for Aerial Objects, in IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025.
[TCAD'25] Y Yu, F Yu, Z Xu, D Wang, M Zhang, A Li, C Liu, Z Tian, X Chen, FedMT: Multi-Task Federated Learning with Competitive GPU Resource Sharing, in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2025.
[Arxiv'25] Y Li, W Qi, X Wang, F Yu, X Wang, Revisiting Pre-trained Language Models for Vulnerability Detection, in submission, 2025.
[Arxiv'25] C Lee, V Paramanayakam, A Karatzas, Y Jian, M Fore, H Liao, F Yu, R Li, I. Anagnostopoulos, D. Stamoulis, Multi-Agent Geospatial Copilots for Remote Sensing Workflows, in submission, 2025.
[NeurIPS'24] C Xu, F Yu, M Li, Z Zheng, Z Xu, J Xiong, X Che. Infinite-Dimensional Feature Interaction, in Conference on Neural Information Processing Systems (NeurIPS), 2024.
[ICML'24] C. Xu, F. Yu, Z. Xu, N Inkawhich, and X. Chen. Out-of-Distribution Detection via Deep Multi-Comprehension Ensemble, in Proceedings of International Conference on Machine Learning (ICML), 2024.
[ICECS'24] S Singh, M Fore, A Karatzas, C Lee, Y Jian, L Shangguan, F Yu, I. Anagnostopoulos, D. Stamoulis, LLM-dcache: Improving Tool-augmented LLMs with GPT-Driven Localized Data Caching, in the 31st IEEE International Conference on Electronics, Circuits and Systems (ICECS), 2024.
[ECCV Workshop'24] Y. Jian, F. Yu, Qi Zhang, W. Levine, B. Dubbs, and N. karianakis. Online Learning via Memory: Retrieval-Augmented Detector Adaptation, in European Conference on Computer Vision (ECCV), Human-Inspired Computer Vision Workshop, Proceeding Track, 2024.
[ACSAC'24] Y. Li, Xinda Wang, F. Yu, L. Sun, W. Zhang, and X. Wang. FedCAP: Robust Federated Learning via Customized Aggregation and Personalization, in Annual Computer Security Applications Conference (ACSAC), 2024.
[ASP-DAC'24] C. Xu, F. Yu, Z. Xu, C. Liu, J. Xiong, and X. Chen. QuadraNet: Improving High-Order Neural Interaction Efficiency with Hardware-Aware Quadratic Neural Networks, in Proceedings of 29th Asia and South Pacific Design Automation Conference (Best Paper Award Nomination), 2024.
[TCAD'24] F. Yu, Z. Xu, L. Shangguan, D. Wang, D. Stamoulis, R. Madhok, N. Karianakis, A. Li, C. Liu, Y. Chen, and X. Chen. Rethinking Latency-aware DNN Design with GPU Tail Effect Analysis, in the Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2024.
[ICCAD'24] Y. Yu, F. Yu, M. Zhang, D. Wang, T. Soyata, C. Liu, and X. Chen, GACER: Granularity-Aware ConcurrEncy Regulation for Multi-Tenant Deep Learning, in the 43rd IEEE/ACM International Conference on Computer-Aided Design (ICCAD), 2024.
[NeurIPS Workshop'23] Y. Jian, F. Yu, S. Singh, D. Stamoulis. Stable Diffusion For Aerial Object Detection, in NeurIPS 2023 Workshop on Synthetic Data Generation with Generative AI (NeurIPS Synthetic4ML), Dec. 2023.
[DAC'23] Y. Yu, F. Yu, X. Sheng, C. Liu, and X. Chen. EagleRec: Edge-Scale Recommendation System Acceleration with Inter-Stage Parallelism Optimization on GPUs, in Proceedings of the 56th Design Automation Conference (DAC), Sep. 2023.
[Arxiv'23] M. Zhang, F. Yu, Y. Yu, M. Zhang, A. Li, and X. Chen, FedHC: A Scalable Federated Learning Framework for Heterogeneous and Resource-Constrained Clients, in submission, 2023.
[MLSys'22] Z. Xu, F. Yu, J. Xiong, and X. Chen. QuadraLib: A Performant Quadratic Neural Network Library for Architecture Optimization and Design Exploration, in the Fifth Conference on Machine Learning and Systems (MLSys), Sep. 2022 (Outstanding Paper Award).
[MLSys-CrossFL'22] Y. Yu, F. Yu, Z. Xu, X. Chen. Powering Multi-Task Federated Learning with Competitive GPU Resource Sharing, accepted in the CrossFL Workshop co-located with MLSys, Sep. 2022 (Best Poster Award).
[MLSys-AIOps'22] F. Yu, Y. Yu, D. Wang, M. Zhang, L. Shangguan, C. Liu, T. Soyata, X. Chen. A Survey of Multi-Tenant Deep Learning Inference on GPU, accepted in the Cloud Intelligence / AIOps Workshop co-located with MLSys, Sep. 2022.
[EuroSys'22 Poster] F. Yu, Z. Xu, T. Shen, D. Stamoulis, L. Shangguan, D. Wang, M. Zhang, X. Tong, R. Madhok, C. Zhao, X. Li, N. Karianakis, D. Lymberopoulos, C. Liu, A. Li, Y. Chen, and X. Chen. Rethinking Latency-aware DNN Design with GPU Tail Effect Analysis, poster accepted in the 17th European Conference on Computer Systems (EuroSys), Apr 2022.
[ICDCS'22] EK Ardestani, C Kim, SJ Lee, L Pan, V Rampersad, J Axboe, B Agrawal, F. Yu, A. Yu, T. Le, H. Yuen, S. Juluri, A. Nanda, M. Wodekar, D. Mudigere, K. Nair, M. Naumov, C. Peterson, M. Smelyanskiy, V. Rao. Supporting Massive DLRM Inference Through Software Defined Memory, in the 42nd IEEE International Conference on Distributed Computing Systems (ICDCS), Jul. 2022.
[TCAD'22] F. Yu, Z. Xu, C. Liu, D. Stamoulis, D. Wang, Y. Wang, and X. Chen. AntiDoteX: Attention-based Dynamic Optimization for Neural Network Runtime Efficiency, in the Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), June 2022.
[WACV '22] F. Yu, D. Wang, Y. Chen, Nikos. Karianakis, P. Yu, D. Lymberopoulos, S. Lu, W. Shi, X. Chen, SC-UDA: Style and Content Gap Aware Unsupervised Domain Adaptation for Object Detection, in Proceedings of the Winter Conference on Applications of Computer Vision (WACV), Jan. 2022.
[WACV '22] Z. Xu, F. Yu, Z. Wu, H. Wang, and X. Chen. FalCon: Fine-grained Feature Map Sparsity Computing with Decomposed Convolutions for Inference Optimization, in Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), Jan. 2022.
[KDD '21] F. Yu, W. Zhang, Z. Qin, Z. Xu, D. Wang, C. Liu, Z. Tian, and X. Chen. Fed^2: Feature Aligned Federated Learning, in Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Aug. 2021.
[ICCAD '21] F. Yu, S. Bray, D. Wang, L. Shangguan, X. Tang, C. Liu and X. Chen. Automated Runtime-Aware Scheduling for Multi-Tenant DNN Inference on GPU, in Proceedings of the 40th IEEE International Conference on Computer-Aided Design (ICCAD), Nov. 2021.
[DAC'21] Z. Xu, F. Yu, J. Xiong, X. Chen. Helios: Heterogeneity-Aware Federated Learning with Dynamically Balanced Collaboration, in Proceedings of the 58th Design Automation Conference (DAC), Dec. 2021.
[TCAD'21] Z. Qin, F. Yu, Z. Xu, C. Liu, X. Chen. CaptorX: A Class-Adaptive Convolutional Neural Network Reconfiguration Framework, in the Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), May 2021.
[DATE'20] F. Yu, C. Liu, D. Wang, Y. Wang, and X. Chen. AntiDOte: Attention-based Dynamic Optimization for Neural Network Runtime Efficiency, in the 23rd Design Automation and Test in Europe Conference (Best Paper Award Nomination), Mar. 2020.
[DATE'20] F. Yu, Z. Qin, D. Wang, P. Xu, C. Liu, T. Zhi, and X. Chen. DC-CNN: Computational Flow Redefinition for Efficient CNN Inference through Model Structural Decoupling, in the 23rd Design Automation and Test in Europe Conference (DATE), Mar. 2020.
[TCAD'20] F. Yu, Z. Qin, C. Liu, D. Wang, X. Chen. REIN the RobuTS: Robust DNN-based Image Recognition in Autonomous Driving Systems, in the Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), Sep. 2020.
[TCAD'20] Z. Xu, F. Yu, Z. Qin, C. Liu, X. Chen. DirectX: Dynamic Resource-Aware CNN Reconfiguration Framework for Real-Time Mobile Applications, in the Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), May 2020.
[CVPR Workshop'20] F. Yu, D. Wang, Y. Chen, Nikos. Karianakis, P. Yu, D. Lymberopoulos, X. Chen, Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning (CVPR V4AS Workshop), Jun. 2020.
[ASP-DAC'20] X. Ma, G. Yuan, S. Lin, C. Ding, F. Yu, T. Liu, W. Wen, X. Chen, Y. Wang. Tiny but Accurate: A Pruned, Quantized and Optimized Memristor Crossbar Framework for Ultra-Efficient DNN Implementation, in Proc. of the 25th Asia and South Pacific Design Automation Conference, Jan. 2020.
[IJCAI'19] F. Yu, Z. Qin, C. Liu, L. Zhao, Y. Wang, X. Chen. Interpreting and Evaluating Adversarial Robustness, in Proceedings of the 28th International Joint Conference of Artificial Intelligence (IJCAI), Aug. 2019.
[KDD'19] J. Wang, F. Yu, X. Chen, L. Zhao. ADMM for Efficient Deep Learning with Global Convergence, in Proceedings of the 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Aug. 2019.
[DAC '19] F. Yu*, Z. Xu*, C. Liu, and X. Chen. MASKER: Adaptive Mobile Security Enhancement against Automatic Speech Recognition in Eavesdropping. in Proceedings of the 56th Design Automation Conference (DAC), Jun. 2019.
[DAC '19] Z. Xu, F. Yu, C. Liu, and X. Chen. ReForm: Static and Dynamic Resource-Aware DNN Reconfiguration Framework for Mobile Devices. in Proceedings of the 56th Design Automation Conference (DAC), Jun. 2019.
[BMVC'19] Z. Qin, F. Yu, C. Liu, X. Chen. Functionality-Oriented Convolutional Filter Pruning, in the Proceedings of 30th British Machine Vision Conference (BMVC), Sep. 2019.
[ASP-DAC '19] F. Yu, C. Liu, and X. Chen. REIN: A Robust Training Method for Enhancing Generalization Ability of Neural Networks in Autonomous Driving Systems. in Proceedings of the 24th Asia and South Pacific Design Automation Conference (ASP-DAC), Jan. 2019.
[ASP-DAC '19] Z. Xu, F. Yu, C. Liu, and X. Chen. HAMPER: High-Performance Adaptive Mobile Security Enhancement against Malicious Speech and Image Recognition. in Proceedings of the 24th Asia and South Pacific Design Automation Conference (ASP-DAC), Jan. 2019.
[ASP-DAC '19] Z. Qin, F. Yu, C. Liu, and X. Chen. CAPTOR: A Class Adaptive Filter Pruning Framework for Convolutional Neural Networks in Mobile Applications. in Proceedings of the 24th Asia and South Pacific Design Automation Conference (ASP-DAC), Jan. 2019.
[NIPS Workshop'18] F. Yu, Z. Qin, and X. Chen. Distilling Critical Paths in Convolutional Neural Networks. in the 32nd Conference on Neural Information Processing Systems, Workshop on Compact Deep Neural Networks with industrial applications, Dec. 2018.
[NIPS Workshop'18] Z. Qin, F. Yu, C. Liu, and X. Chen. Demystifying Neural Network Filter Pruning. in the 32nd Conference on Neural Information Processing Systems, Workshop on Compact Deep Neural Networks with industrial applications, Dec. 2018.
[ISLPED '18] Z. Xu, Z. Qin, F. Yu, C. Liu, and X. Chen. DiReCt: Resource-Aware Dynamic Model Reconfiguration for Convolutional Neural Network in Mobile Systems. in Proceedings of the 23rd ACM/IEEE International Symposium on Low Power Electronics and Design, No. 37, pp. 1 6, Jul. 2018.
[ISVLSI '18] C. Liu, Q. Dong, F. Liu, F. Yu, and X. Chen. ReRise: An Adversarial Example Restoration System for Neuromorphic Computing Security. in Proceedings of the 17th IEEE Computer Society Annual Symposium on VLSI, pp. 470 475, Jul. 2018.
[DAC WIP'18] F. Yu, Q. Dong, and X. Chen. ASP: A Fast Adversarial Attack Example Generation Framework based on Adversarial Saliency Prediction. in the 55th Design Automation Conference, Working In Progress, Jun. 2018.
[MFC '18] Z. Qin, F. Yu, C. Liu, X. Chen. How convolutional neural networks see the world - A survey of convolutional neural network visualization methods. in the Journal of Mathematical Foundations of Computing, pp.149 180, May. 2018.