Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 5 of 5 for “"Conditional flow matching"”.

  1. Conditional flow matching for fast generation of LES-quality instantaneous urban microclimate fields

    … we developed a generative surrogate model using Conditional Flow Matching (CFM) with optimal transport to reconstruct and generate plausible instantaneous multi-variable urban microclimate snapshots. The model learns a time-dependent vector field to transport Gaussian noise into physically …

    concordia Download PDF for Conditional flow matching for fast generation of LES-quality instantaneous urban microclimate fields (opens in a new tab)

  2. Generative modeling of topological and spatiotemporal data

    … We formulate human trajectory prediction as conditional flow matching, enabling correlated multimodal futures to be generated together as scene-level hypotheses. We then scale this approach to autonomous-driving motion prediction by jointly producing multiple trajectories, learning confidence …

    ubc Repository record for Generative modeling of topological and spatiotemporal data (opens in a new tab) Download PDF for Generative modeling of topological and spatiotemporal data (opens in a new tab)

  3. INFORMATION-GEOMETRIC LATENT ENCODING FOR 3D GAUSSIAN SPLATTING

    … multi-view rendering supervision, and conditional flow matching. On a disjoint ShapeSplat split, evaluation over 128 held-out objects yields mean center Chamfer distance of 1.54 ×10−3, PSNR of 25.57 ±2.64 dB, SSIM of 0.956 ±0.016, and LPIPS of 0.124 ±0.032. Under a matched …

    ecu Repository record for INFORMATION-GEOMETRIC LATENT ENCODING FOR 3D GAUSSIAN SPLATTING (opens in a new tab)

  4. Testing the Semigroup Property of Generative Models for Dynamical Systems - Developing a test based on the Chapman–Kolmogorov equation

    Surrogate models for molecular dynamics, particularly those based on generative artificial intelligence, offer an efficient way to model molecular systems across timescales that may be difficult to access through simulation. However, such models should remain consistent with the underlying physics. …

    chalmers Repository record for Testing the Semigroup Property of Generative Models for Dynamical Systems - Developing a test based on the Chapman–Kolmogorov equation (opens in a new tab)

  5. Neural Inverse Microstructure Design with Bayesian Scale-Bridging

    … experimental datasets, providing an anchor for conditional flow-based generative models to perform the larger inversion. This neural parameterization of continuous families of transport maps, lays the foundation for the stochastic exploration of microstructure and processing pathways, providing …

    gatech Repository record for Neural Inverse Microstructure Design with Bayesian Scale-Bridging (opens in a new tab)