Author

Jing-Li Lin

h-index 7 View on Semantic Scholar

We have 2 of 10 papers

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.

#artificial intelligence Preprint Sep 2026

Beyond Visual Quality: Evaluating Physical Consistency under Ego-Motion with EgoGenEval

EgoGenEval introduces EgoGenEval, a geometry-grounded, pose-free benchmark designed to evaluate the physical consistency of visual generators under ego-motion, and shows that pairwise supervision does not reliably improve camera-motion grounding and scene-state preservation together.

Yi-Lin Long, Chen-Ming Zhu, Zi-Tang Gou et al. · 0 citations

Jul 2026

G2TAM: Geometry Grounded Track Anything Model

The Geometry Grounded Tracking Anything Model is proposed, a unified framework for promptable instance tracking in 3D using only unordered RGB images or videos and delivers strong cross-view consistency, promptable instance spatial tracking, video object segmentation and spatial reconstruction, establishing a foundatio...

Chen-Ming Zhu, Peizhou Cao, Jing-Li Lin et al. · arXiv.org · 0 citations