Get Started
Home
Topics
Search
Library
Research questionHow can generative models capture kinetic dynamics on Lie groups from partial endpoint observations without flattening the manifold?Lie-group-valued states have non-Euclidean geometry, while endpoint data may constrain positions but not velocities. A generative model must preserve intrinsic dynamics and account for the unobserved endpoint variables.
AI
Machine Learning
Research Paper
Statistical Machine Learning
Latest papersRecent research connected to this question, newest first.Schrödinger Bridges on Lie Group Manifolds for Probabilistic Intrinsic GenerationThe source studies states consisting of group positions and velocities, with partial endpoint observations. It provides computational treatments for compact Abelian and non-Abelian groups and reports experiments involving molecular torsions, SO(3), U(n), and protein conformational transitions.research paper · Sep 2, 2026
Related questions
How can unknown nonlinear ODE dynamics and time-varying external forces be learned from one trajectory without physics priors?How can object-centric world models predict manipulation-induced changes without accumulating errors that derail planning?How can sign-language production models generate grammatical non-manual features without losing expressive variation?How can learned graph simulators preserve contact history for accurate long-horizon granular-dynamics rollouts?