REVIEW 5 cited by
Sampling Generative Networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Sampling Generative Networks
read the original abstract
We introduce several techniques for sampling and visualizing the latent spaces of generative models. Replacing linear interpolation with spherical linear interpolation prevents diverging from a model's prior distribution and produces sharper samples. J-Diagrams and MINE grids are introduced as visualizations of manifolds created by analogies and nearest neighbors. We demonstrate two new techniques for deriving attribute vectors: bias-corrected vectors with data replication and synthetic vectors with data augmentation. Binary classification using attribute vectors is presented as a technique supporting quantitative analysis of the latent space. Most techniques are intended to be independent of model type and examples are shown on both Variational Autoencoders and Generative Adversarial Networks.
Forward citations
Cited by 5 Pith papers
-
Inverting the Generation Process of Denoising Diffusion Implicit Models: Empirical Evaluation and a Novel Method
A hybrid gradient-descent-plus-fixed-point method for inverting DDIM improves initial latent recovery and reconstruction accuracy over prior techniques on three datasets, with a new self-interpolation test exposing we...
-
Minimizing Collateral Damage in Activation Steering
Activation steering is cast as constrained optimization that minimizes collateral damage by weighting perturbations according to the empirical second-moment matrix of activations instead of assuming isotropy.
-
Variational Autoencoder-Based Black-Box Adversarial Attack on Collaborative DNN Inference
AdVAR-DNN employs a variational autoencoder to create untraceable adversarial samples that compromise black-box collaborative DNN inference by exploiting model partitioning information exchange, achieving high misclas...
-
Scene-aware Prediction of Diverse Human Movement Goals
CVAE model predicts diverse human movement goals from RGB scenes and poses, demonstrating generalization on GTA-IM and PROX datasets.
-
Steered Generation via Gradient-Based Optimization on Sparse Query Features
Prototype-Based Sparse Steering decomposes query activations with SAEs and optimizes sparse features via gradients to steer LLM outputs toward specific behaviors.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.