Yimo Cai

Yimo Cai

3rd-year Undergraduate in Electronic Engineering at Tsinghua University. Researching 3D Vision and Multimodal Models.

Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

Published in Preprint, 2026

Download paper here

Abstract: Spatial-TTT presents a streaming visual-based spatial intelligence strategy with test-time training for MLLMs.

Key Contributions:

  • Training Dataset Construction.
  • Part of the paper and visualization.