GEAR aligns Ricci curvatures in latent spaces of models to create a unified transfer learning architecture, achieving 14.4% and 8.3% performance gains on 23 molecular task pairs under random and scaffold splits.
Adityanarayanan Radhakrishnan, Max Ruiz Luyten, Neha Prasad, and Caroline Uhler
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Particle Diffusion Matching uses diffusion-guided random walk searches to align challenging standard and ultra-widefield retinal images, claiming state-of-the-art benchmark performance.
citing papers explorer
-
Geometric Embedding Alignment via Curvature Matching in Transfer Learning
GEAR aligns Ricci curvatures in latent spaces of models to create a unified transfer learning architecture, achieving 14.4% and 8.3% performance gains on 23 molecular task pairs under random and scaffold splits.
-
Particle Diffusion Matching: Random Walk Correspondence Search for the Alignment of Standard and Ultra-Widefield Fundus Images
Particle Diffusion Matching uses diffusion-guided random walk searches to align challenging standard and ultra-widefield retinal images, claiming state-of-the-art benchmark performance.