AI RESEARCH
CoEditor++: Instruction-based Visual Editing via Cognitive Reasoning
arXiv CS.CV
•
ArXi:2603.05518v1 Announce Type: cross Recent advances in large multimodal models (LMMs) have enabled instruction-based image editing, allowing users to modify visual content via natural language descriptions. However, existing approaches often struggle with high-level semantic reasoning and visual consistency, particularly under ambiguous or complex instructions. To address these challenges, we propose CoEditor++, a cognitively structured