KARL: Knowledge-Aware Reasoning and Reinforcement Learning for Knowledge-Intensive Visual Grounding

Xinyu Maโˆ— , Ziyang Dingโˆ— , Zhicong Luo, Chi Chen, Zonghao Guo, Xuebo Liu, Derek F. Wong, Zhen Zhao, Xiaoyi Feng, Maosong Sun

This is the official checkpoints of KARL, an MLLM enhanced with Knowledge-Aware Reinforcement Learning.

Downloads last month
12
Safetensors
Model size
9B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Oscar-dzy/KARL

Finetuned
(754)
this model

Paper for Oscar-dzy/KARL