1

Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge Devices
Generative large language models (LLMs) have garnered significant attention due to their exceptional capabilities in various AI tasks. …
Shengyuan Ye, Bei Ouyang, Liekang Zeng, Tianyi Qian, Xiaowen Chu, Jian Tang, Xu Chen
Dec 6, 2024
Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge Devices
Generative large language models (LLMs) have garnered significant attention due to their exceptional capabilities in various AI tasks. …
Shengyuan Ye, Bei Ouyang, Liekang Zeng, Tianyi Qian, Xiaowen Chu, Jian Tang, Xu Chen
Cite
Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge Devices
MIX3D: A Mixed Representation for Communication-Efficient Distributed 3DGS Training
3D Gaussian Splatting (3DGS) has recently emerged as a prominent technique in novel view synthesis. The superior performance of 3DGS …
Ke Luo, Kongyange Zhao, Shengyuan Ye, Tao Ouyang, Xu Chen
Oct 8, 2024
Paper Demo
MEGA: Mesh-Aligned 3DGS Towards Geometry-Preserving Online Reconstruction
3D Gaussian Splatting (3DGS) has recently emerged as a significant advancement in 3D scene reconstruction, offering high-resolution, …
Ke Luo, Shengyuan Ye, Tao Ouyang, Zhi Zhou
Oct 3, 2024
Paper Demo
Pluto and Charon: A Time and Memory Efficient Collaborative Edge AI Framework for Personal LLMs Fine-Tuning
Large language models (LLMs) have unlocked a plethora of powerful applications at the network edge, such as intelligent personal …
Bei Ouyang, Shengyuan Ye, Liekang Zeng, Tianyi Qian, Jingyi Li, Xu Chen
Jun 11, 2024
Paper Slides
Pluto and Charon: A Time and Memory Efficient Collaborative Edge AI Framework for Personal LLMs Fine-Tuning
Large language models (LLMs) have unlocked a plethora of powerful applications at the network edge, such as intelligent personal …
Bei Ouyang, Shengyuan Ye, Liekang Zeng, Tianyi Qian, Jingyi Li, Xu Chen
Cite Paper Slides
Pluto and Charon: A Time and Memory Efficient Collaborative Edge AI Framework for Personal LLMs Fine-Tuning
Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer Inference
Transformer-based models have unlocked a plethora of powerful intelligent applications at the edge, such as voice assistant in smart …
Shengyuan Ye, Jiangsu Du, Liekang Zeng, Wenzhong Ou, Xiaowen Chu, Yutong Lu, Xu Chen
Dec 1, 2023
Paper Slides Videos Press
Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer Inference
Transformer-based models have unlocked a plethora of powerful intelligent applications at the edge, such as voice assistant in smart …
Shengyuan Ye, Jiangsu Du, Liekang Zeng, Wenzhong Ou, Xiaowen Chu, Yutong Lu, Xu Chen
Cite Paper Slides Videos Press
Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer Inference
Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devices
On-device Deep Neural Network (DNN) training has been recognized as crucial for privacy-preserving machine learning at the edge. …
Shengyuan Ye, Liekang Zeng, Xiaowen Chu, Guoliang Xing, Xu Chen
Nov 22, 2023
Paper Demo
Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devices
On-device Deep Neural Network (DNN) training has been recognized as crucial for privacy-preserving machine learning at the edge. …
Shengyuan Ye, Liekang Zeng, Xiaowen Chu, Guoliang Xing, Xu Chen
Cite Paper Demo Slides Poster
Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devices