Audio-SDS uses a pretrained text-to-audio diffusion model as a frozen critic to optimize parameters of FM synthesizers, impact simulators, and source separation latents, matching text prompts without task-specific training.
Jacnet: Learning functions with structured jacobians
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Neural networks are trained to learn an approximate mapping from an input domain to a target domain. Incorporating prior knowledge about true mappings is critical to learning a useful approximation. With current architectures, it is challenging to enforce structure on the derivatives of the input-output mapping. We propose to use a neural network to directly learn the Jacobian of the input-output function, which allows easy control of the derivative. We focus on structuring the derivative to allow invertibility and also demonstrate that other useful priors, such as $k$-Lipschitz, can be enforced. Using this approach, we can learn approximations to simple functions that are guaranteed to be invertible and easily compute the inverse. We also show similar results for 1-Lipschitz functions.
citation-role summary
method 1
citation-polarity summary
years
2025 3roles
method 1polarities
use method 1representative citing papers
A new differentiable layer with convex parameter space universally approximates generalized convex functions and their gradients, enabling single-level reformulations of bilevel problems in optimal transport and multi-good auctions.
JacobianODE learns Jacobians from data to quantify directional control in nonlinear systems and shows sensory-to-cognitive control strengthening in a trained working-memory RNN.
citing papers explorer
-
Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond
Audio-SDS uses a pretrained text-to-audio diffusion model as a frozen critic to optimize parameters of FM synthesizers, impact simulators, and source separation latents, matching text prompts without task-specific training.
-
Universal Representation of Generalized Convex Functions and their Gradients
A new differentiable layer with convex parameter space universally approximates generalized convex functions and their gradients, enabling single-level reformulations of bilevel problems in optimal transport and multi-good auctions.
-
Characterizing control between interacting subsystems with deep Jacobian estimation
JacobianODE learns Jacobians from data to quantify directional control in nonlinear systems and shows sensory-to-cognitive control strengthening in a trained working-memory RNN.