Výsledky vyhledávání - "Song, Xinshuai"

Report

Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method

Autor: Song, Xinshuai, Chen, Weixing, Liu, Yang, Chen, Weikai, Li, Guanbin, Lin, Liang

Existing Vision-Language Navigation (VLN) methods primarily focus on single-stage navigation, limiting their effectiveness in multi-stage and long-horizon tasks within complex and dynamic environments. To address these limitations, we propose a novel

Externí odkaz: http://arxiv.org/abs/2412.09082

Zobrazit plný text záznamu

Report

InfiniteWorld: A Unified Scalable Simulation Framework for General Visual-Language Robot Interaction

Autor: Ren, Pengzhen, Li, Min, Luo, Zhen, Song, Xinshuai, Chen, Ziwei, Liufu, Weijia, Yang, Yixuan, Zheng, Hao, Xu, Rongtao, Huang, Zitong, Ding, Tongsheng, Xie, Luyang, Zhang, Kaidong, Fu, Changfei, Liu, Yang, Lin, Liang, Zheng, Feng, Liang, Xiaodan

Realizing scaling laws in embodied AI has become a focus. However, previous work has been scattered across diverse simulation platforms, with assets and models lacking unified interfaces, which has led to inefficiencies in research. To address this,

Externí odkaz: http://arxiv.org/abs/2412.05789

Zobrazit plný text záznamu

Report

MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments

Autor: Liu, Yang, Song, Xinshuai, Jiang, Kaixuan, Chen, Weixing, Luo, Jingzhou, Li, Guanbin, Lin, Liang

With the surge in the development of large language models, embodied intelligence has attracted increasing attention. Nevertheless, prior works on embodied intelligence typically encode scene or historical memory in an unimodal manner, either visual

Externí odkaz: http://arxiv.org/abs/2402.00290

Zobrazit plný text záznamu