RAAG: Ratio Aware Adaptive Guidance

• URL: http://arxiv.org/abs/2508.03442v1
• Date: Tue, 05 Aug 2025 13:41:05 GMT
• Title: RAAG: Ratio Aware Adaptive Guidance
• Authors: Shangwen Zhu, Qianyu Peng, Yuting Hu, Zhantao Yang, Han Zhang, Zhao Pu, Ruili Feng, Fan Cheng,
• Abstract summary: We show that the earliest reverse steps are acutely sensitive to the guidance scale, owing to a pronounced spike in the relative strength (RATIO) of conditional to unconditional predictions.<n>We propose a simple, theoretically grounded, RATIO-aware adaptive guidance schedule that automatically dampens the guidance scale at early steps based on the evolving RATIO.<n>Our approach enables up to 3x faster sampling while maintaining or improving generation quality, robustness, and semantic alignment.
• Score: 7.2455669888408085
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Flow-based generative models have recently achieved remarkable progress in image and video synthesis, with classifier-free guidance (CFG) becoming the standard tool for high-fidelity, controllable generation. However, despite their practical success, little is known about how guidance interacts with different stages of the sampling process-especially in the fast, low-step regimes typical of modern flow-based pipelines. In this work, we uncover and analyze a fundamental instability: the earliest reverse steps are acutely sensitive to the guidance scale, owing to a pronounced spike in the relative strength (RATIO) of conditional to unconditional predictions. Through rigorous theoretical analysis and empirical validation, we show that this RATIO spike is intrinsic to the data distribution, independent of the model architecture, and causes exponential error amplification when paired with strong guidance. To address this, we propose a simple, theoretically grounded, RATIO-aware adaptive guidance schedule that automatically dampens the guidance scale at early steps based on the evolving RATIO, using a closed-form exponential decay. Our method is lightweight, requires no additional inference overhead, and is compatible with standard flow frameworks. Experiments across state-of-the-art image (SD3.5, Lumina) and video (WAN2.1) models demonstrate that our approach enables up to 3x faster sampling while maintaining or improving generation quality, robustness, and semantic alignment. Extensive ablation studies further confirm the generality and stability of our schedule across models, datasets, and hyperparameters. Our findings highlight the critical role of stepwise guidance adaptation in unlocking the full potential of fast flow-based generative models.

Related papers

• How Much To Guide: Revisiting Adaptive Guidance in Classifier-Free Guidance Text-to-Vision Diffusion Models [57.42800112251644]
  We propose Step AG, which is a simple, universally applicable adaptive guidance strategy.<n>Our evaluations focus on both image quality and image-text alignment.
  arXiv  Detail & Related papers  (2025-06-10T02:09:48Z)
• Feedback Guidance of Diffusion Models [0.0]
  Interval-Free Guidance (CFG) has become standard for improving sample fidelity in conditional diffusion models.<n>We propose FeedBack Guidance (FBG), which uses a state-dependent coefficient to self-regulate guidance amounts based on need.
  arXiv  Detail & Related papers  (2025-06-06T13:46:32Z)
• Solving Inverse Problems with FLAIR [59.02385492199431]
  Flow-based latent generative models are able to generate images with remarkable quality, even enabling text-to-image generation.<n>We present FLAIR, a novel training free variational framework that leverages flow-based generative models as a prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• Consistent World Models via Foresight Diffusion [56.45012929930605]
  We argue that a key bottleneck in learning consistent diffusion-based world models lies in the suboptimal predictive ability.<n>We propose Foresight Diffusion (ForeDiff), a diffusion-based world modeling framework that enhances consistency by decoupling condition understanding from target denoising.
  arXiv  Detail & Related papers  (2025-05-22T10:01:59Z)
• In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention [52.159541540613915]
  We study how multi-head softmax attention models are trained to perform in-context learning on linear data.<n>Our results reveal that in-context learning ability emerges from the trained transformer as an aggregated effect of its architecture and the underlying data distribution.
  arXiv  Detail & Related papers  (2025-03-17T02:00:49Z)
• Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence [11.400431211239958]
  Diffusion models have emerged as powerful tools for generative modeling.<n>We propose a control framework for fine-tuning diffusion models.<n>We show that PI-FT achieves global convergence at a linear rate.
  arXiv  Detail & Related papers  (2024-12-24T04:55:46Z)
• Guided Flows for Generative Modeling and Decision Making [55.42634941614435]
  We show that Guided Flows significantly improves the sample quality in conditional image generation and zero-shot text synthesis-to-speech. Notably, we are first to apply flow models for plan generation in the offline reinforcement learning setting ax speedup in compared to diffusion models.
  arXiv  Detail & Related papers  (2023-11-22T15:07:59Z)
• Soft ascent-descent as a stable and flexible alternative to flooding [6.527016551650139]
  We propose a softened, pointwise mechanism called SoftAD that downweights points on the borderline, limits the effects of outliers, and retains the ascent-descent effect of flooding. We demonstrate how SoftAD can realize classification accuracy competitive with flooding while enjoying a much smaller loss generalization gap and model norm.
  arXiv  Detail & Related papers  (2023-10-16T02:02:56Z)
• Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulation [26.520247496906492]
  In this work, we analyze if fully data-driven fluid solvers that utilize an autoregressive rollout based on conditional diffusion models are a viable option to address this challenge.<n>To quantitatively and qualitatively benchmark the performance of various flow prediction approaches, three challenging 2D scenarios including incompressible and transonic flows, as well as isotropic turbulence are employed.<n>We find that even simple diffusion-based approaches can outperform multiple established flow prediction methods in terms of accuracy and temporal stability, while being on par with state-of-the-art stabilization techniques like unrolling at training time.
  arXiv  Detail & Related papers  (2023-09-04T18:01:42Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods [24.190587751595455]
  Weak supervision is a popular method for building machine learning models without relying on ground truth annotations. Existing approaches use latent variable estimation to model the noisy sources. We show that for a class of latent variable models highly applicable to weak supervision, we can find a closed-form solution to model parameters. We use this insight to build FlyingSquid, a weak supervision framework that runs orders of magnitude faster than previous weak supervision approaches.
  arXiv  Detail & Related papers  (2020-02-27T07:51:50Z)

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.