Picture for Weikai Huang

Weikai Huang

Generate Any Scene: Evaluating and Improving Text-to-Vision Generation with Scene Graph Programming

Add code
Dec 11, 2024
Viaarxiv icon

ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models

Add code
Dec 09, 2024
Viaarxiv icon

Task Me Anything

Add code
Jun 17, 2024
Figure 1 for Task Me Anything
Figure 2 for Task Me Anything
Figure 3 for Task Me Anything
Figure 4 for Task Me Anything
Viaarxiv icon

m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks

Add code
Mar 21, 2024
Viaarxiv icon

LesionPaste: One-Shot Anomaly Detection for Medical Images

Add code
Mar 12, 2022
Figure 1 for LesionPaste: One-Shot Anomaly Detection for Medical Images
Figure 2 for LesionPaste: One-Shot Anomaly Detection for Medical Images
Figure 3 for LesionPaste: One-Shot Anomaly Detection for Medical Images
Figure 4 for LesionPaste: One-Shot Anomaly Detection for Medical Images
Viaarxiv icon