Imaginative Generative AI: Crossing the Entropy Wall into Worlds Beyond Imitation

• URL: http://arxiv.org/abs/2608.09385v2
• Date: Tue, 11 Aug 2026 16:38:45 GMT
• Title: Imaginative Generative AI: Crossing the Entropy Wall into Worlds Beyond Imitation
• Abstract summary: We introduce Imaginative Generative AI (IGA), a framework that makes diversity part of the target-distribution design problem.<n>IGA selects one whose spectral diversity reaches a prescribed level.<n>We develop the theory of this entropy-constrained projection and show that, under a KL anchor to a pretrained generator, the optimum satisfies a self-consistent exponential-tilt relation.
• Score: 20.403981727850237
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative AI models are primarily designed to imitate the data distribution, an objective that neither corrects diversity lost by a learned generator nor defines how generation should extend beyond the diversity of the data itself. We introduce Imaginative Generative AI (IGA), a framework that makes diversity part of the target-distribution design problem: among distributions close to a reference, IGA selects one whose spectral diversity reaches a prescribed level. Diversity is measured by the von Neumann entropy of the generated distribution's kernel covariance operator in a fixed representation space, providing a reference-free representation-guided measure of how broadly probability mass occupies embedding directions. The spectral entropy of the population data distribution defines an Entropy Wall. Below the wall, IGA performs diversity repair, recovering variation that a learned generator has lost while remaining within the diversity level of the data. Beyond the wall, the data distribution itself becomes infeasible, and IGA deliberately departs from it to produce distributions with greater representation-relative spectral diversity, an operational notion of imaginative generation. These regimes form a single regularization path from imitation to imagination and define an i.i.d. target distribution at each prescribed diversity level. We develop the theory of this entropy-constrained projection and show that, under a KL anchor to a pretrained generator, the optimum satisfies a self-consistent exponential-tilt relation. This characterization leads to IGA Guidance, a retraining-free inference-time method for score-based and diffusion models, including DDPM and DDIM samplers. Experiments on synthetic and vision benchmarks demonstrate diversity repair below the Entropy Wall and controlled spectral extrapolation beyond it.

Related papers

• Diverse Sampling in Diffusion Models with Marginal Preserving Particle Guidance [13.27396716172129]
  We present EDDY (Exact-marginal Diversification via Divergence-free dYnamics), a guidance mechanism for diffusion and flow matching models.<n>Experiments on synthetic distributions and text-to-image generation show that EDDY improves diversity while maintaining strong distributional fidelity compared to common baselines.
  arXiv  Detail & Related papers  (2026-05-07T16:49:12Z)
• Exposing Diversity Bias in Deep Generative Models: Statistical Origins and Correction of Diversity Error [19.594704501292778]
  We compare the diversity of samples generated by state-of-the-art models with that of test samples drawn from the target data distribution.<n>We find that test data consistently attains substantially higher Vendi and RKE diversity scores than the generated samples.
  arXiv  Detail & Related papers  (2026-02-16T12:15:34Z)
• Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation [51.305316234962554]
  We propose textbfDRIFT (textbfDivetextbfRsity-textbfIncentivized Reinforcement textbfFine-textbfTuning for Versatile Image Generation), an innovative framework that systematically incentivizes output throughout the on-policy fine-tuning process.<n>DRIFT achieves superior dominance regarding task alignment and generation diversity, yielding a $ 9.08%!sim! 43.46%$ increase in diversity equivalent alignment levels and a $ 59.65
  arXiv  Detail & Related papers  (2026-01-18T13:25:43Z)
• Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models [59.331993845831946]
  Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. This paper provides the first theoretical study towards understanding the influence of guidance on diffusion models in the context of Gaussian mixture models.
  arXiv  Detail & Related papers  (2024-03-03T23:15:48Z)
• StyleGenes: Discrete and Efficient Latent Distributions for GANs [149.0290830305808]
  We propose a discrete latent distribution for Generative Adversarial Networks (GANs) Instead of drawing latent vectors from a continuous prior, we sample from a finite set of learnable latents. We take inspiration from the encoding of information in biological organisms.
  arXiv  Detail & Related papers  (2023-04-30T23:28:46Z)
• Source-free Domain Adaptation Requires Penalized Diversity [60.04618512479438]
  Source-free domain adaptation (SFDA) was introduced to address knowledge transfer between different domains in the absence of source data. In unsupervised SFDA, the diversity is limited to learning a single hypothesis on the source or learning multiple hypotheses with a shared feature extractor. We propose a novel unsupervised SFDA algorithm that promotes representational diversity through the use of separate feature extractors.
  arXiv  Detail & Related papers  (2023-04-06T00:20:19Z)
• Structure-preserving GANs [6.438897276587413]
  We introduce structure-preserving GANs as a data-efficient framework for learning distributions. We show that we can reduce the discriminator space to its projection on the invariant discriminator space. We contextualize our framework by building symmetry-preserving GANs for distributions with intrinsic group symmetry.
  arXiv  Detail & Related papers  (2022-02-02T16:40:04Z)
• GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue [95.23775347605923]
  Building on the success of deep learning, Generative Adversarial Networks (GANs) provide a modern approach to learn a probability distribution from observed samples. GANs often suffer from the mode collapse issue where the generator fails to capture all existing modes of the input distribution. We take an information-theoretic approach and maximize a variational lower bound on the entropy of the generated samples to increase their diversity.
  arXiv  Detail & Related papers  (2020-09-24T19:34:37Z)
• Generative Model without Prior Distribution Matching [26.91643368299913]
  Variational Autoencoder (VAE) and its variations are classic generative models by learning a low-dimensional latent representation to satisfy some prior distribution. We propose to let the prior match the embedding distribution rather than imposing the latent variables to fit the prior.
  arXiv  Detail & Related papers  (2020-09-23T09:33:24Z)
• Unsupervised Controllable Generation with Self-Training [90.04287577605723]
  controllable generation with GANs remains a challenging research problem. We propose an unsupervised framework to learn a distribution of latent codes that control the generator through self-training. Our framework exhibits better disentanglement compared to other variants such as the variational autoencoder.
  arXiv  Detail & Related papers  (2020-07-17T21:50:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.