A generative model writes programs in a relational constraint DSL and uses bootstrapping to learn object placement distributions that align more closely with human annotations than data-driven or LLM baselines.
Mode Regularized Generative Adversarial Networks
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
Although Generative Adversarial Networks achieve state-of-the-art results on a variety of generative tasks, they are regarded as highly unstable and prone to miss modes. We argue that these bad behaviors of GANs are due to the very particular functional shape of the trained discriminators in high dimensional spaces, which can easily make training stuck or push probability mass in the wrong direction, towards that of higher concentration than that of the data generating distribution. We introduce several ways of regularizing the objective, which can dramatically stabilize the training of GAN models. We also show that our regularizers can help the fair distribution of probability mass across the modes of the data generating distribution, during the early phases of training and thus providing a unified solution to the missing modes problem.
verdicts
UNVERDICTED 4representative citing papers
GalCatDiff applies category embeddings and a novel Astro-RAB block inside diffusion models to produce galaxy images whose color and size distributions match observations more closely than prior generative approaches.
HighSync is a diffusion-based lip synchronization system that operates natively at 512x512 resolution by eliminating data leakage to enforce genuine audio dependence and reports state-of-the-art results on quality and sync metrics.
A conditional Wasserstein GAN generates complete kinematic event summaries for IBD-CC, NC, and NuEElastic electron neutrino interactions that match GENIE distributions in 1D marginals and correlations.
citing papers explorer
-
Learning to Place Objects with Programs and Iterative Self Training
A generative model writes programs in a relational constraint DSL and uses bootstrapping to learn object placement distributions that align more closely with human annotations than data-driven or LLM baselines.
-
Category-based Galaxy Image Generation via Diffusion Models
GalCatDiff applies category embeddings and a novel Astro-RAB block inside diffusion models to produce galaxy images whose color and size distributions match observations more closely than prior generative approaches.
-
HighSync: High-Quality Lip Synchronization via Latent Diffusion Models
HighSync is a diffusion-based lip synchronization system that operates natively at 512x512 resolution by eliminating data leakage to enforce genuine audio dependence and reports state-of-the-art results on quality and sync metrics.
-
Conditional Wasserstein GAN for Simulating Neutrino Event Summaries using Incident Energy of Electron Neutrinos
A conditional Wasserstein GAN generates complete kinematic event summaries for IBD-CC, NC, and NuEElastic electron neutrino interactions that match GENIE distributions in 1D marginals and correlations.