Filtered Posterior Mean Collections unify prior models of diffusion generalization and demonstrate performance gains through soft relaxations and source distribution augmentations on image datasets.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.LG 4roles
dataset 1polarities
use dataset 1representative citing papers
Neural scaling laws are invariant under bijective data transformations and change predictably with information resolution ρ under non-bijective transformations, enabling cross-domain transport of fitted exponents.
MoRAM learns continually by adding small rank-1 adapters that act as associative memory items, using input-key similarity to retrieve and mix only the relevant adapters at test time.
A mathematical review of flow matching techniques for generative models, showing characterizations via couplings, kernels, and processes, with application to inverse problems.
citing papers explorer
-
Filtered Posterior Mean Collections: A Unified Framework for Analytical Models of Diffusion Generalization
Filtered Posterior Mean Collections unify prior models of diffusion generalization and demonstrate performance gains through soft relaxations and source distribution augmentations on image datasets.
-
On the Invariance and Generality of Neural Scaling Laws
Neural scaling laws are invariant under bijective data transformations and change predictably with information resolution ρ under non-bijective transformations, enabling cross-domain transport of fitted exponents.
-
Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts
MoRAM learns continually by adding small rank-1 adapters that act as associative memory items, using input-key similarity to retrieve and mix only the relevant adapters at test time.
-
Flow Matching: Markov Kernels, Stochastic Processes and Transport Plans
A mathematical review of flow matching techniques for generative models, showing characterizations via couplings, kernels, and processes, with application to inverse problems.