ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution
Paper
•
2510.12793
•
Published
•
3
InternVL3.5-Flash
InternVL3.5-Flash is a fast variant of InternVL3.5 using semantic aware dynamic high-resolution strategy.
-
-
OpenGVLab/InternVL3_5-241B-A28B-Flash
Image-Text-to-Text • 242B • Updated • 118 • 4 -
OpenGVLab/InternVL3_5-38B-Flash
Image-Text-to-Text • 40B • Updated • 384 • 5 -
OpenGVLab/InternVL3_5-30B-A3B-Flash
Image-Text-to-Text • 31B • Updated • 3.28k • 5 -
OpenGVLab/InternVL3_5-14B-Flash
Image-Text-to-Text • 15B • Updated • 261 • 5 -
OpenGVLab/InternVL3_5-8B-Flash
Image-Text-to-Text • 9B • Updated • 1.37k • 4 -
OpenGVLab/InternVL3_5-4B-Flash
Image-Text-to-Text • 5B • Updated • 1.33k • 3 -
OpenGVLab/InternVL3_5-2B-Flash
Image-Text-to-Text • 2B • Updated • 4.67k • 3 -
OpenGVLab/InternVL3_5-1B-Flash
Image-Text-to-Text • 1B • Updated • 1.22k • 4