Picture for Hongyuan Zhang

Hongyuan Zhang

Growing a Twig to Accelerate Large Vision-Language Models

Add code
Mar 18, 2025
Viaarxiv icon

Adv-CPG: A Customized Portrait Generation Framework with Facial Adversarial Attacks

Add code
Mar 11, 2025
Viaarxiv icon

Text2World: Benchmarking Large Language Models for Symbolic World Model Generation

Add code
Feb 18, 2025
Viaarxiv icon

Enhance Vision-Language Alignment with Noise

Add code
Dec 17, 2024
Viaarxiv icon

Edge Contrastive Learning: An Augmentation-Free Graph Contrastive Learning Model

Add code
Dec 15, 2024
Figure 1 for Edge Contrastive Learning: An Augmentation-Free Graph Contrastive Learning Model
Figure 2 for Edge Contrastive Learning: An Augmentation-Free Graph Contrastive Learning Model
Figure 3 for Edge Contrastive Learning: An Augmentation-Free Graph Contrastive Learning Model
Figure 4 for Edge Contrastive Learning: An Augmentation-Free Graph Contrastive Learning Model
Viaarxiv icon

Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning?

Add code
Dec 11, 2024
Viaarxiv icon

G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation

Add code
Nov 27, 2024
Viaarxiv icon

SignEye: Traffic Sign Interpretation from Vehicle First-Person View

Add code
Nov 18, 2024
Viaarxiv icon

Deep Learning Techniques for Automatic Lateral X-ray Cephalometric Landmark Detection: Is the Problem Solved?

Add code
Sep 24, 2024
Viaarxiv icon

Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noise

Add code
Aug 19, 2024
Viaarxiv icon