{
  "abstract": "Reward fine-tuning aims to update a pre-trained flow-based generative model to improve the downstream reward of its generated samples. Existing methods typically formulate this problem as sampling from a reward-tilted distribution, the solution to a KL-regularized reward-maximization problem. Here, we introduce an optimal transport regularizer built directly from the pre-trained drift. Unlike KL reward tilting, the resulting objective transports individual samples toward higher reward rather than reweighting the base distribution. We show that the resulting problem is equivalent to a deterministic optimal control problem on the flow. Given a pre-trained flow map, this equivalence yields a simulation-free reinforcement learning algorithm for fine-tuning generative flows. We call the resulting framework Wasserstein-Tilted Flow Maps (WTF), the first end-to-end fine-tuning recipe native to flow maps. The output is a fine-tuned flow map that retains strong reward-aligned performance at few-step inference budgets without post-hoc distillation. Experiments on ImageNet-256 and text-to-image show that WTF achieves higher reward with comparable or higher diversity than baselines, while requiring up to $280\\times$ less training compute. More broadly, we argue that accelerated samplers such as flow maps are essential infrastructure for efficient post-training, and that the dominant KL-regularized formulation is only one of many choices worth revisiting.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.27033",
  "author_total": 8,
  "authors": [
    {
      "name": "Abbas Mammadov"
    },
    {
      "name": "Jerry Y. Huang"
    },
    {
      "name": "Justin Lin"
    },
    {
      "name": "Partha Kaushik"
    },
    {
      "name": "Sheel Shah"
    },
    {
      "name": "Kartik Nair"
    },
    {
      "name": "Yee Whye Teh"
    },
    {
      "name": "Nicholas M. Boffi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2sz31bw3sat8k.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.27033",
  "fulltext_url": null,
  "id": "2sz31bw3sat8k",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.27033",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1707|Generative Adversarial Networks and Image Synthesis"
    ]
  ],
  "openalex": "W7214214134",
  "pdf_url": "https://arxiv.org/pdf/2609.27033",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-12",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2sz31bw3sat8k.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:26Z",
      "native_id": "2609.27033",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.27033"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "WTF?! Simulation-Free Reinforcement Learning with Wasserstein-Tilted Flow Maps",
  "title_text": "WTF?! Simulation-Free Reinforcement Learning with Wasserstein-Tilted Flow Maps",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:26Z",
  "url": "https://research.draconitic.com/paper/2sz31bw3sat8k",
  "venue": "arXiv",
  "versions": []
}