Duality Models: An Embarrassingly Simple One-step Generation Paradigm

• URL: http://arxiv.org/abs/2602.17682v1
• Date: Wed, 04 Feb 2026 17:16:22 GMT
• Title: Duality Models: An Embarrassingly Simple One-step Generation Paradigm
• Abstract summary: "One input, one output" paradigm enforces a partition of the training budget.<n> allocating sufficient samples to the multi-step objective leaves the few-step generation undertrained.<n>We propose Duality Models (DuMo) via a "one input, dual output" paradigm.
• Score: 46.10673908377537
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Consistency-based generative models like Shortcut and MeanFlow achieve impressive results via a target-aware design for solving the Probability Flow ODE (PF-ODE). Typically, such methods introduce a target time $r$ alongside the current time $t$ to modulate outputs between a local multi-step derivative ($r = t$) and a global few-step integral ($r = 0$). However, the conventional "one input, one output" paradigm enforces a partition of the training budget, often allocating a significant portion (e.g., 75% in MeanFlow) solely to the multi-step objective for stability. This separation forces a trade-off: allocating sufficient samples to the multi-step objective leaves the few-step generation undertrained, which harms convergence and limits scalability. To this end, we propose Duality Models (DuMo) via a "one input, dual output" paradigm. Using a shared backbone with dual heads, DuMo simultaneously predicts velocity $v_t$ and flow-map $u_t$ from a single input $x_t$. This applies geometric constraints from the multi-step objective to every sample, bounding the few-step estimation without separating training objectives, thereby significantly improving stability and efficiency. On ImageNet 256 $\times$ 256, a 679M Diffusion Transformer with SD-VAE achieves a state-of-the-art (SOTA) FID of 1.79 in just 2 steps. Code is available at: https://github.com/LINs-lab/DuMo

Related papers

• Three-Body Scattering for Generative Modeling [17.851305398372794]
  We show that a proper distributional energy can induce sample-level motion and provide direct regression supervision for a one-step generator.<n>Three-Body Scattering Modeling for generation turns the energy distance into a constant-size per-projectile interaction.<n>We provide a design map relating diffusion-related supervision, Drift-like dynamics, and GAN-like objectives.
  arXiv  Detail & Related papers  (2026-07-20T17:38:12Z)
• Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation [50.55853275866995]
  Real-time interactive video generation requires low-latency, streaming, and controllable rollout.<n>In this paper, we study a more aggressive setting: frame-wise autoregression with only 1--2 sampling steps.<n>We propose textbfCausal Forcing++, a principled and scalable pipeline.
  arXiv  Detail & Related papers  (2026-05-14T17:46:36Z)
• Meta Flow Maps enable scalable reward alignment [22.109809498990362]
  Controlling generative models is computationally expensive.<n>This is because optimal alignment with a reward function--whether via inference-time steering or fine-tuning--requires estimating the value function.<n>We introduce Meta Flow Maps (MFMs), a framework consistency models and flow maps into extending the regime.
  arXiv  Detail & Related papers  (2026-01-20T19:39:56Z)
• 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)
• Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models [100.28111930893188]
  Some of today's best generative models still require hundreds to thousands of neural function evaluations to compute a single likelihood.<n>We present fast flow joint distillation (F2D2), a framework that simultaneously reduces the number of NFEs required for both sampling and likelihood evaluation by two orders of magnitude.<n>F2D2 is modular, compatible with existing flow-based few-step sampling models, and requires only an additional divergence prediction head.
  arXiv  Detail & Related papers  (2025-12-02T10:48:20Z)
• Improved Mean Flows: On the Challenges of Fastforward Generative Models [81.10827083963655]
  MeanFlow (MF) has recently been established as a framework for one-step generative modeling.<n>Here, we address key challenges in both the training objective and the guidance mechanism.<n>Our reformulation yields a more standard regression problem and improves the training stability.<n>Overall, our $textbfimproved MeanFlow$ ($textbfiMF$) method, trained entirely from scratch, achieves $textbf1.72$ FID with a single function evaluation (1-NFE) on ImageNet 256$times$256.
  arXiv  Detail & Related papers  (2025-12-01T18:59:49Z)
• AlphaFlow: Understanding and Improving MeanFlow Models [74.64465762009475]
  We show that the MeanFlow objective naturally decomposes into two parts: trajectory flow matching and trajectory consistency.<n>Motivated by these insights, we introduce $alpha$-Flow, a broad family of objectives that unifies trajectory flow matching, Shortcut Model, and MeanFlow.<n>When trained from scratch on class-conditional ImageNet-1K 256x256 with vanilla DiT backbones, $alpha$-Flow consistently outperforms MeanFlow across scales and settings.
  arXiv  Detail & Related papers  (2025-10-23T17:45:06Z)
• Marginal Flow: a flexible and efficient framework for density estimation [6.94175385834858]
  Current density modeling approaches suffer from at least one of the following shortcomings: expensive training, slow inference, approximate likelihood, mode collapse or architectural constraints.<n>We propose a simple yet powerful framework that overcomes these limitations altogether.<n>We define our model $q_theta(x)$ through a parametric distribution $q(x|w)$ with latent parameters $w$.<n>Instead of directly optimizing the latent variables $w$, our idea is to marginalize them out by sampling $w$ from a learnable distribution $q_theta(w)$, hence the name Marginal Flow
  arXiv  Detail & Related papers  (2025-09-30T13:21:13Z)
• 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)
• Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models [49.81937966106691]
  We develop a suite of non-asymptotic theory towards understanding the data generation process of diffusion models. In contrast to prior works, our theory is developed based on an elementary yet versatile non-asymptotic approach.
  arXiv  Detail & Related papers  (2023-06-15T16:30:08Z)

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.