notesum.ai

Published at October 23

ROCKET-1: Master Open-World Interaction with Visual-Temporal Context Prompting

cs.CY
cs.AI
cs.HC
cs.IR

Released Date: October 23, 2024

Authors: Shaofei Cai1, Zihao Wang1, Kewei Lian1, Zhancun Mu1, Xiaojian Ma2, Anji Liu3, Yitao Liang4

Aff.: 1PKU; 2BIGAI; 3UCLA; 4B

Arxiv: https://arxiv.org/abs/2410.17856v1