Picture for Jing Zhang

Jing Zhang

The University of Sydney, Australia

TFANet: Three-Stage Image-Text Feature Alignment Network for Robust Referring Image Segmentation

Add code
Sep 16, 2025
Viaarxiv icon

Patch Progression Masked Autoencoder with Fusion CNN Network for Classifying Evolution Between Two Pairs of 2D OCT Slices

Add code
Aug 27, 2025
Viaarxiv icon

Handling Students Dropouts in an LLM-driven Interactive Online Course Using Language Models

Add code
Aug 24, 2025
Viaarxiv icon

Structural Energy-Guided Sampling for View-Consistent Text-to-3D

Add code
Aug 23, 2025
Viaarxiv icon

S5: Scalable Semi-Supervised Semantic Segmentation in Remote Sensing

Add code
Aug 17, 2025
Viaarxiv icon

REX-RAG: Reasoning Exploration with Policy Correction in Retrieval-Augmented Generation

Add code
Aug 12, 2025
Viaarxiv icon

TEFormer: Texture-Aware and Edge-Guided Transformer for Semantic Segmentation of Urban Remote Sensing Images

Add code
Aug 08, 2025
Viaarxiv icon

MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs

Add code
Aug 07, 2025
Viaarxiv icon

How and Why: Taming Flow Matching for Unsupervised Anomaly Detection and Localization

Add code
Aug 07, 2025
Viaarxiv icon

SPEX: A Vision-Language Model for Land Cover Extraction on Spectral Remote Sensing Images

Add code
Aug 07, 2025
Viaarxiv icon