Siyuan Huang 0004 Haonan Chang Yuhan Liu Yimeng Zhu Hao Dong 0003 Abdeslam Boularias Peng Gao 0007 Hongsheng Li 0001 A3VLM: Actionable Articulation-Aware Vision Language Model. 1675-1690 2024 CoRL https://proceedings.mlr.press/v270/huang25b.html conf/corl/2024 db/conf/corl/corl2024.html#0004CLZ0B0024