Picture for Yongxin Liao

Yongxin Liao

TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models

Add code
Apr 14, 2024
Figure 1 for TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models
Figure 2 for TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models
Figure 3 for TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models
Figure 4 for TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models
Viaarxiv icon