2025
DWIM: Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation & Instruct-Masking Tuning
ICCV 2025poster
Visual reasoning (VR), which is crucial in many fields for enabling human-like visual understanding, remains highly challenging. Recently, compositional visual reasoning approaches, which leverage the reasoning abilities of large language models (LLMs) with integrated tools to solve problems, have s…