Picture for Zhengyu Zhang

Zhengyu Zhang

Channel Semantic Characterization for Integrated Sensing and Communication Scenarios: From Measurements to Modeling

Add code
Mar 03, 2025
Viaarxiv icon

External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation

Add code
Feb 26, 2025
Figure 1 for External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation
Figure 2 for External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation
Figure 3 for External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation
Figure 4 for External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation
Viaarxiv icon

Vision-Aided Channel Prediction Based on Image Segmentation at Street Intersection Scenarios

Add code
Jan 27, 2025
Viaarxiv icon

Personalized Interpolation: An Efficient Method to Tame Flexible Optimization Window Estimation

Add code
Jan 23, 2025
Viaarxiv icon

Evaluating Human Perception of Novel View Synthesis: Subjective Quality Assessment of Gaussian Splatting and NeRF in Dynamic Scenes

Add code
Jan 13, 2025
Viaarxiv icon

Mixture of Hidden-Dimensions Transformer

Add code
Dec 10, 2024
Figure 1 for Mixture of Hidden-Dimensions Transformer
Figure 2 for Mixture of Hidden-Dimensions Transformer
Figure 3 for Mixture of Hidden-Dimensions Transformer
Figure 4 for Mixture of Hidden-Dimensions Transformer
Viaarxiv icon

Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching

Add code
Oct 23, 2024
Figure 1 for Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching
Figure 2 for Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching
Figure 3 for Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching
Figure 4 for Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching
Viaarxiv icon

Non-stationarity Characteristics in Dynamic Vehicular ISAC Channels at 28 GHz

Add code
Mar 01, 2024
Viaarxiv icon

Characterization of Wireless Channel Semantics: A New Paradigm

Add code
Mar 01, 2024
Viaarxiv icon

A Cluster-Based Statistical Channel Model for Integrated Sensing and Communication Channels

Add code
Mar 01, 2024
Figure 1 for A Cluster-Based Statistical Channel Model for Integrated Sensing and Communication Channels
Figure 2 for A Cluster-Based Statistical Channel Model for Integrated Sensing and Communication Channels
Figure 3 for A Cluster-Based Statistical Channel Model for Integrated Sensing and Communication Channels
Figure 4 for A Cluster-Based Statistical Channel Model for Integrated Sensing and Communication Channels
Viaarxiv icon