2 citations · 5 across the 13 of their papers we have counts for
13 papers
Beyond Greedy Chunking: SLO-Aware Sliding-Window Scheduling for LLM Inference
Yuansheng Chen, Yue Zhang, Xuan Mo +2
With the rapid growth of interactive applications in large language model (LLM) online services, maintaining high system throughput while ensuring user-perceived latency has become…
A Predictive and Synergistic Two-Layer Scheduling Framework for LLM Serving
Yue Zhang, Yuansheng Chen, Xuan Mo +3
LLM inference serving typically scales out with a two-tier architecture: a cluster router distributes requests to multiple inference engines, each of which then in turn performs it…
MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS
Mo Xuan, Zhang yue, Wu Weigang
Model-as-a-Service (MaaS) platforms face diverse Service Level Objective (SLO) requirements stemming from various large language model (LLM) applications, manifested in contextual…
Chain of Methodologies: Scaling Test Time Computation without Training
Cong Liu, Jie Wu, Weigang Wu +3
Large Language Models (LLMs) often struggle with complex reasoning tasks due to insufficient in-depth insights in their training data, which are typically absent in publicly availa…
Analysis of Asynchronous Federated Learning: Unraveling the Interactions between Gradient Compression, Delay, and Data Heterogeneity
Diying Yang, Yingwei Hou, Weigang Wu
In practical federated learning (FL), the large communication overhead between clients and the server is often a significant bottleneck. Gradient compression methods can effectivel…
Grey-Box Fuzzing in Constrained Ultra-Large Systems: Lessons for SE Community
Jiazhao Yu, Yanlun Tu, Zhanlei Zhang +5
Testing ultra-large microservices-based FinTech systems presents significant challenges, including restricted access to production environments, complex dependencies, and stringent…
Cool-Fusion: Fuse Large Language Models without Training
Cong Liu, Xiaojun Quan, Yan Pan +3
We focus on the problem of fusing two or more heterogeneous large language models (LLMs) to leverage their complementary strengths. One of the challenges of model fusion is high co…
FedCME: Client Matching and Classifier Exchanging to Handle Data Heterogeneity in Federated Learning
Jun Nie, Danyang Xiao, Lei Yang +1
Data heterogeneity across clients is one of the key challenges in Federated Learning (FL), which may slow down the global model convergence and even weaken global model performance…
PFL-MoE: Personalized Federated Learning Based on Mixture of Experts
Binbin Guo, Yuan Mei, Danyang Xiao +3
Federated learning (FL) is an emerging distributed machine learning paradigm that avoids data sharing among training nodes so as to protect data privacy. Under coordination of the…
Impact of Temporary Fork on the Evolution of Mining Pools in Blockchain Networks: An Evolutionary Game Analysis
Canhui Chen, Xu Chen, Jiangshan Yu +2
Temporary fork is a fundamental phenomenon in many blockchains with proof of work, and the analysis of temporary fork has recently drawn great attention. Different from existing ef…
Garou: An Efficient and Secure Off-Blockchain Multi-Party Payment Hub
Yongjie Ye, Weigang Wu
To mitigate the scalability problem of decentralized cryptocurrencies such as Bitcoin and Ethereum, the payment channel, which allows two parties to perform secure coin transfers w…
Boros: Secure Cross-Channel Transfers via Channel Hub
YongJie Ye, Jingjing Zhang, Weigang Wu +2
The payment channel, which allows two parties to perform micropayments without involving the blockchain, has become a promising proposal to improve the scalability of decentralized…
Exploiting Massive D2D Collaboration for Energy-Efficient Mobile Edge Computing
Xu Chen, Lingjun Pu, Lin Gao +2
In this article we propose a novel Device-to-Device (D2D) Crowd framework for 5G mobile edge computing, where a massive crowd of devices at the network edge leverage the network-as…