Pith. sign in

REVIEW 3 cited by

Active Divergence with Generative Deep Learning -- A Survey and Taxonomy

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2107.05599 v1 pith:MXL4KSV2 submitted 2021-07-12 cs.LG cs.AI

Terence Broad , Sebastian Berns , Simon Colton , Mick Grierson This is my paper · ORCID
classification cs.LGcs.AI
keywords datadeepgenerativeactivecomputationalcreativecreativitydiverge
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Generative deep learning systems offer powerful tools for artefact generation, given their ability to model distributions of data and generate high-fidelity results. In the context of computational creativity, however, a major shortcoming is that they are unable to explicitly diverge from the training data in creative ways and are limited to fitting the target data distribution. To address these limitations, there have been a growing number of approaches for optimising, hacking and rewriting these models in order to actively diverge from the training data. We present a taxonomy and comprehensive survey of the state of the art of active divergence techniques, highlighting the potential for computational creativity researchers to advance these methods and use deep generative models in truly creative systems.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Unboxing Diffusion Models for the Arts: Interactive Model Bending and Practice-Based Explainability

    cs.HC 2026-07 conditional novelty 6.0 of 10

    Bending different layers of a diffusion model's UNet produces distinct and fairly consistent visual effects across seeds and prompts, and an interactive ComfyUI tool lets artists explore these effects hands-on.

  2. The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety

    cs.AI 2026-01 unverdicted novelty 6.0 of 10

    The paper formalizes homogenization in LLMs as a loss of deviance and core entropy, and proposes xeno-reproduction—a structure-aware diversity-pursuit objective—with a proof that diversity and fairness trade off.

  3. Dynamic Reinforcement Learning for Actors

    cs.LG 2025-02 conditional novelty 6.0 of 10

    A reinforcement learning update that adjusts each neuron's input-output sensitivity using TD error can replace external exploration noise and backpropagation through time in small actor-critic tasks.

Pith tools