PRISM is a pre-training method that learns isometric latent embeddings by explicitly recovering surface geodesic distances with a topology-enforcing loss and a two-stage training schedule.
Geodesics in heat: A new approach to computing distance based on heat flow
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
A terrain-adaptive epsilon-constraint MPC with semi-parametric SGP vehicle-terrain model achieves 94% success rate, 24% lower orientation deviation, and 23% better trade-off quality than MPPI and GAKD baselines.
A plug-and-play differentiable model bridging ray and wave optics for hybrid systems that enables end-to-end optimization of planar and conformal diffractive elements.
Method for generating minimum-weight structurally robust shell objects from 3D models using Laplacian parametrization to ensure intersection-free inner boundaries during stress-based thickness optimization.
citing papers explorer
-
From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Data
PRISM is a pre-training method that learns isometric latent embeddings by explicitly recovering surface geodesic distances with a topology-enforcing loss and a two-stage training schedule.
-
A Terrain-Adaptive epsilon-Constraint MPC for Uneven Terrain Kinodynamic Planning
A terrain-adaptive epsilon-constraint MPC with semi-parametric SGP vehicle-terrain model achieves 94% success rate, 24% lower orientation deviation, and 23% better trade-off quality than MPPI and GAKD baselines.
-
A General Differentiable Ray-Wave Framework for Hybrid Refractive-Diffractive System Modeling and Optimization
A plug-and-play differentiable model bridging ray and wave optics for hybrid systems that enables end-to-end optimization of planar and conformal diffractive elements.
-
Structural Design Using Laplacian Shells
Method for generating minimum-weight structurally robust shell objects from 3D models using Laplacian parametrization to ensure intersection-free inner boundaries during stress-based thickness optimization.