Author

Yunyi Li

View on Semantic Scholar

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 Jul 2026

DeforM: Reasoning-Guided Physics-Aware Video Generation via Spatial-Temporal Masking

DeforM is proposed, a reasoning-guided image-to-video generation framework that directs the model's focus toward physics-critical regions, and introduces a VLM-guided physical reasoning module, DeforM-Reason, to identify target objects and generate spatial-temporal masks.

Yunyi Li, Yu Qiao, Yaohui Wang et al. · 0 citations