OpenGVLab/InternVL2_5-78B
Image-Text-to-Text
•
Updated
•
10k
•
191
Jie Shao
hehesang
AI & ML interests
computer vision, ai for science
Recent Activity
authored
a paper
1 day ago
InternVL3: Exploring Advanced Training and Test-Time Recipes for
Open-Source Multimodal Models
upvoted
a
paper
13 days ago
Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual
Editing
Organizations
hehesang's activity
liked
a
model
4 months ago
liked
a
model
11 months ago