Follow
Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond. (arXiv:2310.02071v3 [cs.AI] UPDATED)
Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond. (arXiv:2310.02071v3 [cs.AI] UPDATED)