Paper Detail

Mine, Sample, Render: Test-Time Diversity Alignment Of Generative Models

Kostas Triaridis, Morris E. Sharp, Nebojsa Jojic

huggingface Score 7.0

Published 2026-10-15 · First seen 2026-10-17

General AI

Abstract

Modern generative models produce high-quality individual outputs but struggle to sample diversely, even when explicitly instructed to do so. We introduce MINE-SAMPLE-RENDER (MSR), a test-time approach that externalizes the diversity into an explicit, corpus-derived sampling procedure. Our pipeline (i) mines an interpretable categorical schema from a corpus of real artifacts and supplies statistics for sampling; (ii) samples attribute configurations from the corpus-derived statistics; (iii) uses a generative model purely as a conditional renderer of a sampled configuration. Across weather report generation, user simulation, webpage design, text-to-image generation, and agent-generated 3D assets, we evaluate the diversity and output quality of MSR-guided generation and show that MSR improves alignment with corpus distributions and diversity of generated outputs.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{triaridis2026mine,
  title = {Mine, Sample, Render: Test-Time Diversity Alignment Of Generative Models},
  author = {Kostas Triaridis and Morris E. Sharp and Nebojsa Jojic},
  year = {2026},
  abstract = {Modern generative models produce high-quality individual outputs but struggle to sample diversely, even when explicitly instructed to do so. We introduce MINE-SAMPLE-RENDER (MSR), a test-time approach that externalizes the diversity into an explicit, corpus-derived sampling procedure. Our pipeline (i) mines an interpretable categorical schema from a corpus of real artifacts and supplies statistics for sampling; (ii) samples attribute configurations from the corpus-derived statistics; (iii) uses },
  url = {https://huggingface.co/papers/2610.21185},
  keywords = {test-time sampling, corpus-derived statistics, categorical schema, conditional renderer, diversity alignment, huggingface daily},
  eprint = {2610.21185},
  archiveprefix = {arXiv},
}

Metadata

{}