Create Publications “2025-11-18-linear-combinations-of-gaussian-latents-in-generative-models-interpolation-and-beyond”

Author: cb580

_publications/2025-11-18-linear-combinations-of-gaussian-latents-in-generative-models-interpolation-and-beyond.md

@@ -0,0 +1,38 @@
+---
+layout: publication-single
+title: "Linear combinations of Gaussian latents in generative models:
+  interpolation and beyond"
+abstract: Sampling from generative models has become a crucial tool for
+  applications like data synthesis and augmentation. Diffusion, Flow Matching
+  and Continuous Normalizing Flows have shown effectiveness across various
+  modalities, and rely on Gaussian latent variables for generation. For
+  search-based or creative applications that require additional control over the
+  generation process, it has become common to manipulate the latent variable
+  directly. However, existing approaches for performing such manipulations (e.g.
+  interpolation or forming low-dimensional representations) only work well in
+  special cases or are network or data-modality specific. We propose Combination
+  of Gaussian variables (COG) as a general purpose method to form linear
+  combinations of latent variables while adhering to the assumptions of the
+  generative model. COG is easy to implement yet outperforms recent
+  sophisticated methods for interpolation. As COG naturally addresses the
+  broader task of forming linear combinations, new capabilities are afforded,
+  including the construction of subspaces of the latent space, dramatically
+  simplifying the creation of expressive low-dimensional spaces of
+  high-dimensional objects.
+published: 2025-11-18
+authors:
+  internal_authors:
+    - Carl Henrik Ek
+  external_authors:
+    - family: Bodin
+      given: "Erik "
+    - family: Stere
+      given: "Alexandru I. "
+    - family: Margineantu
+      given: "Dragos D "
+    - family: Moss
+      given: "Henry "
+details:
+  pdf: https://arxiv.org/pdf/2408.08558v4
+  html: https://arxiv.org/abs/2408.08558
+---