How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning

Qian Yang, Ankur Sikarwar, Huy Le, Le Zhang, Zhuan Shi, Perouz Taslakian

By Callan Zhang · May 26, 2026 · Editorial standards →

Summarised from the primary source with AI assistance under human editorial oversight. Turing Wire is not a primary source — read the original for the authoritative account.

Source: arXiv cs.CV