Picture for Jiawei Shao

Jiawei Shao

Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference

Add code
Mar 17, 2025
Viaarxiv icon

VideoScan: Enabling Efficient Streaming Video Understanding via Frame-level Semantic Carriers

Add code
Mar 12, 2025
Viaarxiv icon

Privacy-Enhancing Paradigms within Federated Multi-Agent Systems

Add code
Mar 11, 2025
Viaarxiv icon

Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model

Add code
Mar 06, 2025
Viaarxiv icon

KV-Edit: Training-Free Image Editing for Precise Background Preservation

Add code
Feb 25, 2025
Viaarxiv icon

Dynamics-Aware Gaussian Splatting Streaming Towards Fast On-the-Fly Training for 4D Reconstruction

Add code
Nov 22, 2024
Viaarxiv icon

AI Flow at the Network Edge

Add code
Nov 19, 2024
Figure 1 for AI Flow at the Network Edge
Figure 2 for AI Flow at the Network Edge
Figure 3 for AI Flow at the Network Edge
Figure 4 for AI Flow at the Network Edge
Viaarxiv icon

EVA-Gaussian: 3D Gaussian-based Real-time Human Novel View Synthesis under Diverse Camera Settings

Add code
Oct 02, 2024
Viaarxiv icon

WirelessAgent: Large Language Model Agents for Intelligent Wireless Networks

Add code
Sep 12, 2024
Viaarxiv icon

Task-Oriented Communication for Vehicle-to-Infrastructure Cooperative Perception

Add code
Jul 30, 2024
Viaarxiv icon