Seguir
Sixing Yu
Sixing Yu
PhD, Researcher, Bing Fundamental, Microsoft AI
Dirección de correo verificada de microsoft.com
Título
Citado por
Citado por
Año
Topology-aware network pruning using multi-stage graph embedding and reinforcement learning
S Yu, A Mazaheri, A Jannesari
International conference on machine learning, 25656-25667, 2022
582022
Auto graph encoder-decoder for neural network pruning
S Yu, A Mazaheri, A Jannesari
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
55*2021
Heterogeneous federated learning using dynamic model pruning and adaptive gradient
S Yu, P Nguyen, A Anwar, A Jannesari
2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet …, 2023
46*2023
Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Models
S Yu, JP Muñoz, A Jannesari
Proceedings of the 2024 Joint International Conference on Computational …, 2024
442024
Resource-aware federated learning using knowledge extraction and multi-model fusion
S Yu, W Qian, A Jannesari
arXiv preprint arXiv:2208.07978, 2022
31*2022
Spatl: Salient parameter aggregation and transfer learning for heterogeneous federated learning
S Yu, P Nguyen, W Abebe, W Qian, A Anwar, A Jannesari
SC22: International Conference for High Performance Computing, Networking …, 2022
28*2022
Resource-aware heterogeneous federated learning using neural architecture search
S Yu, P Nguyen, W Abebe, J Stanley, P Munoz, A Jannesari
arXiv preprint arXiv:2211.05716, 2022
132022
The landscape and challenges of HPC research and LLMs
L Chen, NK Ahmed, A Dutta, A Bhattacharjee, S Yu, QI Mahmud, ...
CoRR, 2024
92024
Bridging the gap between foundation models and heterogeneous federated learning
S Yu, JP Muñoz, A Jannesari
arXiv preprint arXiv:2310.00247, 2023
62023
Spatl: salient parameter aggregation and transfer learning for heterogeneous federated learning. In 2022 SC22: International Conference for High Performance Computing …
S Yu, P Nguyen, W Abebe, W Qian, A Anwar, A Jannesari
IEEE Computer Society, 495-508, 2022
62022
Position Paper: The Landscape and Challenges of HPC Research and LLMs
L Chen, NK Ahmed, A Dutta, A Bhattacharjee, S Yu, QI Mahmud, ...
arXiv preprint arXiv:2402.02018, 2024
42024
Towards seamless management of ai models in high-performance computing
S Yu, M Emani, C Liao, PH Lin, T Vanderbruggen, X Shen, A Jannesari
arXiv preprint arXiv:2212.06352, 2022
22022
SuperSAM: Crafting a SAM Supernetwork via Structured Pruning and Unstructured Parameter Prioritization
W Abebe, S Jafari, S Yu, A Dutta, J Strube, NR Tallent, L Guo, P Munoz, ...
arXiv preprint arXiv:2501.08504, 2025
2025
PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation
B Butler, S Yu, A Mazaheri, A Jannesari
SC24: International Conference for High Performance Computing, Networking …, 2024
2024
Resource-Aware Heterogeneous Federated Learning with Specialized Local Models
S Yu, JP Muñoz, A Jannesari
European Conference on Parallel Processing, 389-403, 2024
2024
Topology-aware efficient and transferable model compression using graph representation and reinforcement learning
S Yu
Iowa State University, 2023
2023
GNN-RL compression: topology-aware network pruning using multi-stage graph embedding and reinforcement learning
S Yu, A Mazaheri, A Jannesari
arXiv preprint arXiv:2102.03214 3, 2021
2021
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–17