works on

From the 4 of 121 papers with an AI index.

most citedMSNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation

80 citations

Showing cs.LGShow all

12 papers · 1 filter

cs.LG2026

Hyper-modal Imputation Diffusion Embedding with Dual-Distillation for Federated Multimodal Knowledge Graph Completion

Ying Zhang, Yu Zhao, Xuhui Sui +5

The paper introduces a federated learning framework for multimodal knowledge graph completion that recovers missing multimodal information with a hyper-modal imputation diffusion e…

cs.LG20263 cited

EvoLP: Self-Evolving Latency Predictor for Model Compression in Real-Time Edge Systems

Shuo Huai, Hao Kong, Shiqing Li +5

Edge devices are increasingly utilized for deploying deep learning applications on embedded systems. The real-time nature of many applications and the limited resources of edge dev…

cs.LG20262 cited

Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems

Shuo Huai, Di Liu, Hao Kong +5

Federated Learning (FL) empowers multiple clients to collaboratively learn a model, enlarging the training data of each client for high accuracy while protecting data privacy. Howe…

cs.LG20268 cited

Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalization

Shuo Huai, Di Liu, Hao Kong +4

Deep learning applications have been widely adopted on edge devices, to mitigate the privacy and latency issues of accessing cloud servers. Deciding the number of neurons during th…

cs.LG2026

CausalPOI: Spatio-Temporal Graph-Based Causal Modeling for Cold-Start POI Check-in Forecasting

Zhaoqi Zhang, Miao Xie, Yi Li +3

As urban environments continue to evolve rapidly, accurately modeling the dynamic behaviour of Points of Interest is essential for supporting data-driven urban planning and commerc…

cs.LG2026

Beyond Single Slot: Joint Optimization for Multi-Slot Guaranteed Display Advertising

Zhaoqi Zhang, Jiaming Deng, Miao Xie +5

Guaranteed display advertising is crucial for platform monetization, yet existing methods often operate under a single-slot assumption, limiting their ability to optimize allocatio…