AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

GeoWorld: Geometric World Models

Zeyu Zhang, Danning Li, Ian Reid, Richard Hartley

CVPR 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Neuro-symbolic probabilistic layers · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
apply hyperbolic latent space (H-JEPA) plus geometric RL instead of Euclidean V-JEPA 2V-JEPA 2 ViT-g384 · CrossTask T=3 video goalssuccess rate (%): 50.16 -> 51.71Improved
apply GeoWorld instead of V-JEPA 2ViT-g384 · COIN T=4 image goalssuccess rate (%): 23.43 -> 27.79Improved
apply GeoWorld instead of V-JEPA 2ViT-L · CrossTask T=3 image goalssuccess rate (%): 43.33 -> 43.89No clear effect
apply GeoWorld instead of V-JEPA 2ViT-g384 · CrossTask T=4 image goalssuccess rate (%): 31.36 -> 31.48No clear effect
apply GeoWorld instead of V-JEPA 2ViT-g384 · CrossTask T=6 video goalssuccess rate (%): 16.88 -> 18.26Improved
apply GeoWorld instead of V-JEPA 2ViT-g384 · CrossTask video goals mIoU/mAccmIoU (%): COIN T=4 mIoU 94.51 -> 95.84; CrossTask T=3 mIoU 91.73 -> 92.95Mixed
apply GeoWorld instead of V-JEPA 2 on image-goal procedural planningViT-g384 · CrossTask T=3mIoU (%): 69.42 -> 86.55Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy