SoftCFG: Uncertainty-guided Stable Guidance for Visual Autoregressive Model

• URL: http://arxiv.org/abs/2510.00996v2
• Date: Thu, 02 Oct 2025 09:32:57 GMT
• Title: SoftCFG: Uncertainty-guided Stable Guidance for Visual Autoregressive Model
• Abstract summary: Autoregressive (AR) models have emerged as powerful tools for image generation by modeling images as sequences of discrete tokens.<n>We propose SoftCFG, an uncertainty-guided inference method that distributes adaptive perturbations across all tokens in the sequence.<n>Experiments show that SoftCFG significantly improves image quality over standard CFG and state-of-the-art FID on ImageNet 256*256 among autoregressive models.
• Score: 17.298633197256024
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autoregressive (AR) models have emerged as powerful tools for image generation by modeling images as sequences of discrete tokens. While Classifier-Free Guidance (CFG) has been adopted to improve conditional generation, its application in AR models faces two key issues: guidance diminishing, where the conditional-unconditional gap quickly vanishes as decoding progresses, and over-guidance, where strong conditions distort visual coherence. To address these challenges, we propose SoftCFG, an uncertainty-guided inference method that distributes adaptive perturbations across all tokens in the sequence. The key idea behind SoftCFG is to let each generated token contribute certainty-weighted guidance, ensuring that the signal persists across steps while resolving conflicts between text guidance and visual context. To further stabilize long-sequence generation, we introduce Step Normalization, which bounds cumulative perturbations of SoftCFG. Our method is training-free, model-agnostic, and seamlessly integrates with existing AR pipelines. Experiments show that SoftCFG significantly improves image quality over standard CFG and achieves state-of-the-art FID on ImageNet 256*256 among autoregressive models.

Related papers

• Rarity-Aware Discrete Diffusion with Spatially Consistent Decoding for Photo-Realistic Image Super-Resolution [80.28905986756685]
  DiMOO-SR is a rarity-aware multimodal discrete diffusion framework for photo-realistic image Super-Resolution.<n>Experiments on widely used real-world SR benchmarks demonstrate that DiMOO-SR achieves competitive perceptual quality with only a few parallel decoding steps.
  arXiv  Detail & Related papers  (2026-07-20T07:01:01Z)
• Guiding a Diffusion Model by Swapping Its Tokens [16.588428780117752]
  We propose a simple method to enable CFG-like guidance for both conditional and unconditional generation.<n>The key idea is to generate a perturbed prediction via simple token swap operations.<n>Our approach selectively exchanges and recomposes token latents, allowing finer control over perturbation.
  arXiv  Detail & Related papers  (2026-04-09T09:54:49Z)
• UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation [51.41441081823758]
  Unified models capable of interleaved generation have emerged as a promising paradigm.<n>We propose a unified reinforcement learning framework tailored for interleaved generation.<n>Our experiments demonstrate that this unified training recipe significantly enhances image generation quality through reasoning.
  arXiv  Detail & Related papers  (2026-03-24T17:59:17Z)
• SSG: Scaled Spatial Guidance for Multi-Scale Visual Autoregressive Generation [10.295970926059812]
  Visual autoregressive ( VAR) models generate images through next-scale prediction, naturally achieving coarse-to-fine, fast, high-fidelity mirroring human perception.<n>In practice, this hierarchy can drift at inference time, as limited capacity and accumulated error cause the model to deviate from its coarse-to-fine nature.<n>We propose Scaled Spatial Guidance (SSG), training-free, inference-time guidance that steers generation toward the intended hierarchy while maintaining global coherence.
  arXiv  Detail & Related papers  (2026-02-05T10:48:58Z)
• All-in-One Video Restoration under Smoothly Evolving Unknown Weather Degradations [102.94052335735326]
  All-in-one image restoration aims to recover clean images from diverse unknown degradations using a single model.<n>Existing approaches primarily focus on frame-wise degradation variation, overlooking the temporal continuity that naturally exists in real-world degradation processes.<n>We introduce the Smoothly Evolving Unknown Degradations (SEUD) scenario, where both the active degradation set and degradation intensity change continuously over time.
  arXiv  Detail & Related papers  (2026-01-02T02:20:57Z)
• SFTok: Bridging the Performance Gap in Discrete Tokenizers [72.9996757048065]
  We propose textbfSFTok, a discrete tokenizer that incorporates a multi-step iterative mechanism for precise reconstruction.<n>At a high compression rate of only 64 tokens per image, SFTok achieves state-of-the-art reconstruction quality on ImageNet.
  arXiv  Detail & Related papers  (2025-12-18T18:59:04Z)
• HiGFA: Hierarchical Guidance for Fine-grained Data Augmentation with Diffusion Models [82.10385962490051]
  Generative diffusion models show promise for data augmentation.<n>Applying them to fine-grained tasks presents a significant challenge.<n>HiGFA is a hierarchical, confidence-driven orchestration that generates diverse yet faithful synthetic images.
  arXiv  Detail & Related papers  (2025-11-16T10:46:16Z)
• IAR2: Improving Autoregressive Visual Generation with Semantic-Detail Associated Token Prediction [77.06211178777939]
  IAR2 is an advanced autoregressive framework that enables a hierarchical semantic-detail synthesis process.<n>We show that IAR2 sets a new state-of-the-art for autoregressive image generation, achieving a FID of 1.50 on ImageNet.
  arXiv  Detail & Related papers  (2025-10-08T12:08:21Z)
• Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis [79.98107530577576]
  DisCon is a novel framework that reinterprets discrete tokens as conditional signals rather than generation targets.<n>DisCon achieves a gFID score of 1.38 on ImageNet 256$times $256 generation, outperforming state-of-the-art autoregressive approaches by a clear margin.
  arXiv  Detail & Related papers  (2025-07-02T14:33:52Z)
• 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)
• Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking [15.052244821404079]
  We introduce Adaptive-Free Guidance (A-CFG), a novel method that tailors unconditional input by leveraging the model's predictive confidence.<n>A-CFG focuses on areas of ambiguity leading to more effective guidance.<n> Experiments on diverse language generation benchmarks show that A-CFG yields substantial improvements over standard CFG.
  arXiv  Detail & Related papers  (2025-05-26T16:40:22Z)
• Few-Step Diffusion via Score identity Distillation [67.07985339442703]
  Diffusion distillation has emerged as a promising strategy for accelerating text-to-image (T2I) diffusion models.<n>Existing methods rely on real or teacher-synthesized images to perform well when distilling high-resolution T2I diffusion models.<n>We propose two new guidance strategies: Zero-CFG, which disables CFG in the teacher and removes text conditioning in the fake score network, and Anti-CFG, which applies negative CFG in the fake score network.
  arXiv  Detail & Related papers  (2025-05-19T03:45:16Z)
• Entropy Rectifying Guidance for Diffusion and Flow Models [27.673559391846524]
  Entropy Rectifying Guidance (ERG) is a simple and effective guidance mechanism based on inference-time changes in the attention mechanism of state-of-the-art diffusion transformer architectures.<n>ERG results in significant improvements in various generation tasks such as text-to-image, class-conditional and unconditional image generation.
  arXiv  Detail & Related papers  (2025-04-18T10:15:33Z)
• NFIG: Autoregressive Image Generation with Next-Frequency Prediction [50.69346038028673]
  We present textbfNext-textbfFrequency textbfImage textbfGeneration (textbfNFIG), a novel framework that decomposes the image generation process into multiple frequency-guided stages.<n>Our approach first generates low-frequency components to establish global structure with fewer tokens, then progressively adds higher-frequency details, following the natural spectral hierarchy of images.
  arXiv  Detail & Related papers  (2025-03-10T08:59:10Z)
• Frequency Autoregressive Image Generation with Continuous Tokens [31.833852108014312]
  We introduce the frequency progressive autoregressive (textbfFAR) paradigm and instantiate FAR with the continuous tokenizer.<n>We demonstrate the efficacy of FAR through comprehensive experiments on the ImageNet dataset.
  arXiv  Detail & Related papers  (2025-03-07T10:34:04Z)
• Adapting Diffusion Models for Improved Prompt Compliance and Controllable Image Synthesis [43.481539150288434]
  This work introduces a new family of. factor graph Diffusion Models (FG-DMs) FG-DMs models the joint distribution of. images and conditioning variables, such as semantic, sketch,. deep or normal maps via a factor graph decomposition.
  arXiv  Detail & Related papers  (2024-10-29T00:54:00Z)
• CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models [52.29804282879437]
  CFG++ is a novel approach that tackles the offmanifold challenges inherent to traditional CFG. It offers better inversion-to-image generation, invertibility, smaller guidance scales, reduced mode collapse, etc. It can be easily integrated into high-order diffusion solvers and naturally extends to distilled diffusion models.
  arXiv  Detail & Related papers  (2024-06-12T10:40:10Z)
• StraIT: Non-autoregressive Generation with Stratified Image Transformer [63.158996766036736]
  Stratified Image Transformer(StraIT) is a pure non-autoregressive(NAR) generative model. Our experiments demonstrate that StraIT significantly improves NAR generation and out-performs existing DMs and AR methods.
  arXiv  Detail & Related papers  (2023-03-01T18:59:33Z)

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.