location: Orchard View Room
SILO: Few-Step Likelihoods of Flow and Diffusion Models: Applications to Images and Molecules
Abstract Flow and diffusion models define processes that generate samples from progressively less noisy versions of the data distribution. I will present a line of work on estimating the marginal probability densities along these processes, culminating in the density of the data distribution itself. Our methods are both sample-efficient to …
SILO: Distribution Transport with Identifiability: A Signal Processing Perspective on Multimodal Generative AI
Abstract A central objective of modern generative AI is to enable learning and inference across multiple modalities, supporting tasks such as cross-modal generation, multimodal translation, domain transfer, and data fusion. Despite impressive empirical progress, many multimodal AI frameworks still lack solid theoretical foundations, raising concerns about reliability and robustness. In …