Picture for Wenhan Dou

Wenhan Dou

Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding

Add code
Jan 14, 2025
Viaarxiv icon

SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding

Add code
Dec 12, 2024
Figure 1 for SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding
Figure 2 for SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding
Figure 3 for SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding
Figure 4 for SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding
Viaarxiv icon

Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training

Add code
Oct 10, 2024
Figure 1 for Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training
Figure 2 for Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training
Figure 3 for Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training
Figure 4 for Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training
Viaarxiv icon

Parameter-Inverted Image Pyramid Networks

Add code
Jun 06, 2024
Figure 1 for Parameter-Inverted Image Pyramid Networks
Figure 2 for Parameter-Inverted Image Pyramid Networks
Figure 3 for Parameter-Inverted Image Pyramid Networks
Figure 4 for Parameter-Inverted Image Pyramid Networks
Viaarxiv icon