Publications

Conference Papers

Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation

Published in European Conference on Computer Vision (ECCV), 2026

A sim-to-real-consistent framework for interactive open-world mobile manipulation, where agents explore from raw RGB observations and resolve ambiguous instructions by communicating with the user.

Recommended citation: Boyu Mi*, Mengchen Ma*, Yifei Yao*, Xing Gao, Junting Chen, Yangzi Li, Zihou Zhu, Guohao Li, Zhenfei Yin, Tai Wang, Yao Mu, Jiangmiao Pang, Hanqing Wang. (2026). "Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation." ECCV 2026. (* Equal contribution)
Download Paper

Technical Reports

InstructMove: A Text-Indispensable Benchmark for Instruction-Following Manipulation

Published in Technical Report, 2026

A text-indispensable benchmark for instruction-following manipulation, where multiple actions are visually and physically plausible but only one matches the language instruction.

Recommended citation: Mengao Zhao*, Ziang Li*, Chaodong Huang*, Mengchen Ma*, Haoyi Jiang, Yiwei Jin, Xinjie Wang, Yun Du, Xuewu Lin, Taojun Ding, Hongyu Xie, Jackson Jiang, Chunlei Yu, Kaihua Zhang, Lichao Huang, Liu Liu, Tianwei Lin, Zhizhong Su. (2026). "InstructMove: A Text-Indispensable Benchmark for Instruction-Following Manipulation." Technical Report, arXiv:2608.22990. (* Equal contribution)
Download Paper