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

Xinyu Ma∗ , Ziyang Ding∗ , 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.