Picture for Qi Wu

Qi Wu

SCI Institute, UC Davis

Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval

Add code
Mar 21, 2025
Viaarxiv icon

Generalized Tensor-Aided Channel Estimation for Hardware Impaired Device Identification

Add code
Mar 13, 2025
Viaarxiv icon

SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation

Add code
Mar 13, 2025
Viaarxiv icon

Certainly Bot Or Not? Trustworthy Social Bot Detection via Robust Multi-Modal Neural Processes

Add code
Mar 11, 2025
Viaarxiv icon

Dynamic Path Navigation for Motion Agents with LLM Reasoning

Add code
Mar 10, 2025
Viaarxiv icon

MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification

Add code
Mar 10, 2025
Viaarxiv icon

REArtGS: Reconstructing and Generating Articulated Objects via 3D Gaussian Splatting with Geometric and Motion Constraints

Add code
Mar 09, 2025
Viaarxiv icon

mmDEAR: mmWave Point Cloud Density Enhancement for Accurate Human Body Reconstruction

Add code
Mar 04, 2025
Viaarxiv icon

Are Large Vision Language Models Good Game Players?

Add code
Mar 04, 2025
Viaarxiv icon

Ground-level Viewpoint Vision-and-Language Navigation in Continuous Environments

Add code
Feb 26, 2025
Viaarxiv icon