Year: 2025
Type: conference-paper
Abstract: demonstrate that 3DLLM-MEM achieves state-of-the-art performance across various tasks, outperforming the strongest baselines by 16.5% in success rate on 3DMEM-BENCH's most challenging in-the-wild embodied tasks.
DOI: 10.52202/085713-2278
Authors: Wenbo Hu, Yining Hong, Yanjun Wang, Leison Gao, Zibu Wei, Xingcheng Yao, Nanyun Peng, Yonatan Bitton, Idan Szpektor, Kai-Wei Chang
Institutions: University of California, Los Angeles, Google (United States)
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
Award: G5714225502
OpenAlex ID: W4416048748