Author

Zihan Zhou

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

SR-JEPA: Learning Predictive Latent State in 3D Scenes

SR-JEPA is introduced, a point-native JEPA for scene-scale point clouds whose original frozen predictive pathway can be queried at a supplied location and reveals a queryable, compositional 3D predictive state.

Zihan Zhou, Qi-Fu Wen, Xi Zeng · 0 citations