EREC-MLSG: Embodied referring expression comprehension via multimodal large language models and scene graph inference for human-robot assembly interaction
Linyang Yan, Chengjun Chen, Chenggang Dai, Yong Pan. EREC-MLSG: Embodied referring expression comprehension via multimodal large language models and scene graph inference for human-robot assembly interaction. // Robotics and Computer-Integrated Manufacturing. – 2027. – DOI: 10.1016/j.rcim.2026.103466. – URL: https://doi.org/10.1016/j.rcim.2026.103466
Linyang Yan, Chengjun Chen, Chenggang Dai, & Yong Pan (2027). EREC-MLSG: Embodied referring expression comprehension via multimodal large language models and scene graph inference for human-robot assembly interaction. Robotics and Computer-Integrated Manufacturing. https://doi.org/10.1016/j.rcim.2026.103466
Linyang Yan, et al. “EREC-MLSG: Embodied referring expression comprehension via multimodal large language models and scene graph inference for human-robot assembly interaction.” Robotics and Computer-Integrated Manufacturing, 2027. doi:10.1016/j.rcim.2026.103466.
@article{Yan2027,
title = {EREC-MLSG: Embodied referring expression comprehension via multimodal large language models and scene graph inference for human-robot assembly interaction},
author = {Yan, Linyang and Chen, Chengjun and Dai, Chenggang and Pan, Yong},
journal = {Robotics and Computer-Integrated Manufacturing},
year = {2027},
doi = {10.1016/j.rcim.2026.103466},
url = {https://doi.org/10.1016/j.rcim.2026.103466}
}