OSU AIoT-MLSys Lab

Efficient-LLMs-Survey

[TMLR 2024] Efficient Large Language Models: A Survey

DeepAA

[ICLR 2022] "Deep AutoAugment" by Yu Zheng, Zhi Zhang, Shen Yan, Mi Zhang

FedRolex

[NeurIPS 2022] "FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction" by Samiul Alam, Luyang Liu, Ming Yan, and Mi Zhang

arch2vec

[NeurIPS 2020] "Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?" by Shen Yan, Yu Zheng, Wei Ao, Xiao Zeng, Mi Zhang

SVD-LLM

Official Code for "SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression"

FedAIoT

FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things

CATE

[ICML 2021 Oral] "CATE: Computation-aware Neural Architecture Encoding with Transformers" by Shen Yan, Kaiqiang Song, Fei Liu, Mi Zhang

AIoT-MLSys-Lab.github.io

Homepage of OSU AIoT and MLSys Lab

Distream

[SenSys 2020] "Distream: Scaling Live Video Analytics with Workload-Adaptive Distributed Edge Intelligence" by Xiao Zeng, Biyi Fang, Haichen Shen, Mi Zhang

MSUNet

[NeurIPS 2019 Google MicroNet Challenge] MSUNet is an efficient model that won the 4th place in the Google MicroNet Challenge CIFAR-100 Track hosted at NeurIPS 2019 designed by Yu Zheng, Shen Yan, Mi Zhang

Mercury

[SenSys 2021] "Mercury: Efficient On-Device Distributed DNN Training via Stochastic Importance Sampling" by Xiao Zeng, Ming Yan, Mi Zhang

Home.github

MutualNet

[ECCV 2020 Oral] MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution

NELoRa-Sensys

[SenSys 2021] "NELoRa: Towards Ultra-low SNR LoRa Communication with Neural-enhanced Demodulation" by Chenning Li, Hanqing Guo, Shuai Tong, Xiao Zeng, Zhichao Cao, Mi Zhang, Qiben Yan, Li Xiao, Jiliang Wang, Yunhao Liu

PyramidFL

[MobiCom 2022] " PyramidFL: Fine-grained Data and System Heterogeneity-aware Client Selection for Efficient Federated Learning" by Chenning Li, Xiao Zeng, Mi Zhang, and Zhichao Cao.