Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization
Paper
•
2411.10442
•
Published
•
64
InternVL2.5-MPO
Enhancing the Reasoning Ability of MLLMs via Mixed Preference Optimization
-
-
OpenGVLab/InternVL2-8B-MPO
Image-Text-to-Text • Updated • 3.11k • 26 -
OpenGVLab/MMPR
Preview • Updated • 222 • 39 -
OpenGVLab/InternVL2_5-1B-MPO
Image-Text-to-Text • Updated • 6 • 8 -
OpenGVLab/InternVL2_5-2B-MPO
Image-Text-to-Text • Updated • 5 • 8 -
OpenGVLab/InternVL2_5-4B-MPO
Image-Text-to-Text • Updated • 6 • 8 -
OpenGVLab/InternVL2_5-8B-MPO
Image-Text-to-Text • Updated • 39 • 8 -
OpenGVLab/InternVL2_5-26B-MPO
Image-Text-to-Text • Updated • 14 • 8 -
OpenGVLab/InternVL2_5-38B-MPO
Image-Text-to-Text • Updated • 10 • 9 -
OpenGVLab/InternVL2_5-78B-MPO
Image-Text-to-Text • Updated • 14 • 9 -
OpenGVLab/MMPR-v1.1
Preview • Updated • 14 • 8