DWIM: Towards Tool-Aware Visual Reasoning via Discrepancy-Aware Workflow Generation & Instruct-Masking Tuning.
Fucai Ke, Vijay Kumar B. G, Xingjian Leng, Zhixi Cai, Zaid Khan, Weiqing Wang, Pari Delir Haghighi, Hamid Rezatofighi, Manmohan Chandraker
Browse the full ICCV paper archive.