ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling

• URL: http://arxiv.org/abs/2607.19332v1
• Date: Tue, 21 Jul 2026 17:51:38 GMT
• Title: ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling
• Abstract summary: We take a minimalist approach to designing a competitive generative model.<n>For the training objective, we choose Implicit Maximum Likelihood Estimation (IMLE)<n>For the model, we eschew transformers and instead choose a moderately sized convolutional network.
• Score: 6.903463801726018
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative models have undergone many generations of evolution, from VAEs/GANs to diffusion/flow matching. Along the way, the underlying techniques have become more complicated and various beliefs about what drives strong empirical performance have taken hold. Due to the success of diffusion models and flow matching, one of the more common beliefs is the importance of transforming the noise distribution to the data distribution gradually through many small transformations. We ask whether this is truly necessary, and take a minimalist approach to designing a competitive generative model. We start with the bare-bones essentials, namely just a training objective and a model. We purposefully make both simple. For the training objective, we choose Implicit Maximum Likelihood Estimation (IMLE), and eschew more complicated alternatives such as variational inference, adversarial training and numerical integration. For the model, we eschew transformers and instead choose a moderately sized convolutional network. Then we judiciously added elements that are truly essential, which surprisingly do not include iterative denoising. The result is a single-step parameter-efficient generative model that produces high quality samples at fast speed: it achieves an FID of 2.56 on ImageNet 256 and simultaneously attains good precision and recall.

Related papers

• TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows [25.487712175353035]
  We propose TwinFlow, a framework for training 1-step generative models.<n>Our method achieves a GenEval score of 0.83 in 1-NFE on text-to-image tasks.<n>Our approach matches the performance of the original 100-NFE model on GenEval and DPG-Bench benchmarks.
  arXiv  Detail & Related papers  (2025-12-03T07:45:46Z)
• Score-based Idempotent Distillation of Diffusion Models [0.9367224590861915]
  Idempotent generative networks (IGNs) are a new line of generative models based on idempotent mapping to a target manifold.<n>In this work, we unite diffusion and IGNs by distilling idempotent models from diffusion model scores, called SIGN.<n>Our proposed method is highly stable and does not require adversarial losses. We provide a theoretical analysis of our proposed score-based training methods and empirically show that IGNs can be effectively distilled from a pre-trained diffusion model.
  arXiv  Detail & Related papers  (2025-09-25T19:36:10Z)
• Truncated Consistency Models [57.50243901368328]
  Training consistency models requires learning to map all intermediate points along PF ODE trajectories to their corresponding endpoints.<n>We empirically find that this training paradigm limits the one-step generation performance of consistency models.<n>We propose a new parameterization of the consistency function and a two-stage training procedure that prevents the truncated-time training from collapsing to a trivial solution.
  arXiv  Detail & Related papers  (2024-10-18T22:38:08Z)
• One Step Diffusion via Shortcut Models [109.72495454280627]
  We introduce shortcut models, a family of generative models that use a single network and training phase to produce high-quality samples.<n>Shortcut models condition the network on the current noise level and also on the desired step size, allowing the model to skip ahead in the generation process.<n>Compared to distillation, shortcut models reduce complexity to a single network and training phase and additionally allow varying step budgets at inference time.
  arXiv  Detail & Related papers  (2024-10-16T13:34:40Z)
• EMR-Merging: Tuning-Free High-Performance Model Merging [55.03509900949149]
  We show that Elect, Mask & Rescale-Merging (EMR-Merging) shows outstanding performance compared to existing merging methods. EMR-Merging is tuning-free, thus requiring no data availability or any additional training while showing impressive performance.
  arXiv  Detail & Related papers  (2024-05-23T05:25:45Z)
• Multistep Consistency Models [24.443707181138553]
  A 1-step consistency model is a conventional consistency model whereas a $infty$-step consistency model is a diffusion model. By increasing the sample budget from a single step to 2-8 steps, we can train models more easily that generate higher quality samples. We show that our method scales to a text-to-image diffusion model, generating samples that are close to the quality of the original model.
  arXiv  Detail & Related papers  (2024-03-11T15:26:34Z)
• One-Step Diffusion Distillation via Deep Equilibrium Models [64.11782639697883]
  We introduce a simple yet effective means of distilling diffusion models directly from initial noise to the resulting image. Our method enables fully offline training with just noise/image pairs from the diffusion model. We demonstrate that the DEQ architecture is crucial to this capability, as GET matches a $5times$ larger ViT in terms of FID scores.
  arXiv  Detail & Related papers  (2023-12-12T07:28:40Z)
• eP-ALM: Efficient Perceptual Augmentation of Language Models [70.47962271121389]
  We propose to direct effort to efficient adaptations of existing models, and propose to augment Language Models with perception. Existing approaches for adapting pretrained models for vision-language tasks still rely on several key components that hinder their efficiency. We show that by freezing more than 99% of total parameters, training only one linear projection layer, and prepending only one trainable token, our approach (dubbed eP-ALM) significantly outperforms other baselines on VQA and Captioning.
  arXiv  Detail & Related papers  (2023-03-20T19:20:34Z)
• AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [97.50616524350123]
  We build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering. The first model, MinAvgOut, directly maximizes the diversity score through the output distributions of each batch. The second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level. The third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal.
  arXiv  Detail & Related papers  (2020-01-15T18:32:06Z)

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.