Picture for Shangguang Wang

Shangguang Wang

Variational Multi-Modal Hypergraph Attention Network for Multi-Modal Relation Extraction

Add code
Apr 18, 2024
Figure 1 for Variational Multi-Modal Hypergraph Attention Network for Multi-Modal Relation Extraction
Figure 2 for Variational Multi-Modal Hypergraph Attention Network for Multi-Modal Relation Extraction
Figure 3 for Variational Multi-Modal Hypergraph Attention Network for Multi-Modal Relation Extraction
Figure 4 for Variational Multi-Modal Hypergraph Attention Network for Multi-Modal Relation Extraction
Viaarxiv icon

FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression

Add code
Mar 25, 2024
Figure 1 for FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression
Figure 2 for FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression
Figure 3 for FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression
Figure 4 for FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression
Viaarxiv icon

Towards Effective Next POI Prediction: Spatial and Semantic Augmentation with Remote Sensing Data

Add code
Mar 22, 2024
Figure 1 for Towards Effective Next POI Prediction: Spatial and Semantic Augmentation with Remote Sensing Data
Figure 2 for Towards Effective Next POI Prediction: Spatial and Semantic Augmentation with Remote Sensing Data
Figure 3 for Towards Effective Next POI Prediction: Spatial and Semantic Augmentation with Remote Sensing Data
Figure 4 for Towards Effective Next POI Prediction: Spatial and Semantic Augmentation with Remote Sensing Data
Viaarxiv icon

Context-based Fast Recommendation Strategy for Long User Behavior Sequence in Meituan Waimai

Add code
Mar 19, 2024
Figure 1 for Context-based Fast Recommendation Strategy for Long User Behavior Sequence in Meituan Waimai
Figure 2 for Context-based Fast Recommendation Strategy for Long User Behavior Sequence in Meituan Waimai
Figure 3 for Context-based Fast Recommendation Strategy for Long User Behavior Sequence in Meituan Waimai
Figure 4 for Context-based Fast Recommendation Strategy for Long User Behavior Sequence in Meituan Waimai
Viaarxiv icon

FedRDMA: Communication-Efficient Cross-Silo Federated LLM via Chunked RDMA Transmission

Add code
Mar 01, 2024
Figure 1 for FedRDMA: Communication-Efficient Cross-Silo Federated LLM via Chunked RDMA Transmission
Figure 2 for FedRDMA: Communication-Efficient Cross-Silo Federated LLM via Chunked RDMA Transmission
Figure 3 for FedRDMA: Communication-Efficient Cross-Silo Federated LLM via Chunked RDMA Transmission
Figure 4 for FedRDMA: Communication-Efficient Cross-Silo Federated LLM via Chunked RDMA Transmission
Viaarxiv icon

Lightweight Protection for Privacy in Offloaded Speech Understanding

Add code
Jan 22, 2024
Viaarxiv icon

A Survey of Resource-efficient LLM and Multimodal Foundation Models

Add code
Jan 16, 2024
Viaarxiv icon

Rethinking Mobile AI Ecosystem in the LLM Era

Add code
Aug 28, 2023
Figure 1 for Rethinking Mobile AI Ecosystem in the LLM Era
Figure 2 for Rethinking Mobile AI Ecosystem in the LLM Era
Figure 3 for Rethinking Mobile AI Ecosystem in the LLM Era
Figure 4 for Rethinking Mobile AI Ecosystem in the LLM Era
Viaarxiv icon

EdgeMoE: Fast On-Device Inference of MoE-based Large Language Models

Add code
Aug 28, 2023
Viaarxiv icon

Federated Fine-tuning of Billion-Sized Language Models across Mobile Devices

Add code
Aug 26, 2023
Figure 1 for Federated Fine-tuning of Billion-Sized Language Models across Mobile Devices
Figure 2 for Federated Fine-tuning of Billion-Sized Language Models across Mobile Devices
Figure 3 for Federated Fine-tuning of Billion-Sized Language Models across Mobile Devices
Figure 4 for Federated Fine-tuning of Billion-Sized Language Models across Mobile Devices
Viaarxiv icon