Jiang Liu

FDALB: Flow distribution aware load balancing for datacenter networks

2016

We present FDALB, a flow distribution aware load balancing mechanism aimed at reducing flow collisions and achieving high scalability. FDALB, like the most of centralized methods, uses a centralized controller to get the view of …

Spatial-context-aware deep neural network for multi-class image classification

2021 · arXiv (Cornell University)

Multi-label image classification is a fundamental but challenging task in computer vision. Over the past few decades, solutions exploring relationships between semantic labels have made great progress. However, the underlying spatial-contextual information of labels is …

Frequency-mixed Single-source Domain Generalization for Medical Image Segmentation

2023 · arXiv (Cornell University)

The annotation scarcity of medical image segmentation poses challenges in collecting sufficient training data for deep learning models. Specifically, models trained on limited data may not generalize well to other unseen data domains, resulting in …

DeepServe: Serverless Large Language Model Serving at Scale

2025 · arXiv (Cornell University)

In this paper, we propose DEEPSERVE, a scalable and serverless AI platform designed to efficiently serve large language models (LLMs) at scale in cloud environments. DEEPSERVE addresses key challenges such as resource allocation, serving efficiency, …

VSR-Net: Vessel-Like Structure Rehabilitation Network With Graph Clustering

2025 · IEEE Transactions on Image Processing

The morphologies of vessel-like structures, such as blood vessels and nerve fibres, play significant roles in disease diagnosis, e.g., Parkinson's disease. Although deep network-based refinement segmentation and topology-preserving segmentation methods recently have achieved promising results …