VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation

• URL: http://arxiv.org/abs/2605.15661v1
• Date: Fri, 15 May 2026 06:32:49 GMT
• Title: VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation
• Abstract summary: COCO-free guidance (CFG) is the primary control over how strongly text semantics move a flow-based sampler.<n>We propose VAGS, a training-free replacement that multiplies the nominal scale by a bounded factor.<n>VAGS consistently improves structural fidelity and generation quality over fixed CFG and recent trainingfree guidance variants.
• Score: 15.19510801548845
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Classifier-free guidance (CFG) is the primary control over how strongly text semantics move a flow-based sampler, yet standard practice holds its scale fixed across the entire ODE trajectory. This is a fundamental mismatch: early steps are noise-dominated and carry weak semantic signal, while late steps commit image structure and demand stronger directional commitment; more critically, the value of any guidance strength depends on whether the guided velocity is consistent with the model's current dynamics or working against them. We propose \textit{Velocity-Adaptive Guidance Scale} (VAGS), a training-free replacement that multiplies the nominal scale by a bounded factor combining a temporal signal-level term with the cosine similarity between task-relevant velocity fields. For inversion-free editing, VAGS measures the alignment between source- and target-guided velocities, so edit strength at each step reflects local compatibility between preservation and transformation. For generation, VAGS-Gen uses the alignment between unconditional and conditional velocities as the analogous signal. Neither variant requires fine-tuning, auxiliary networks, or extra forward passes, and fixed CFG is recovered as a special case. On PIE-Bench and DIV2K for editing, and COCO17, CUB-200, and Flickr30K for generation, VAGS consistently improves structural fidelity and generation quality over fixed CFG and recent training-free guidance variants. The code is publicly available at https://github.com/Harvard-AI-and-Robotics-Lab/Velocity_Adaptive_Guidance_Scale.

Related papers

• Balancing Emotional Alignment and Semantic Consistency in Image Generation via Reinforcement Learning with Valence-Arousal Anchoring [55.57242007016976]
  Continuous emotion control in text-to-image generation requires a model to improve affective alignment without changing the objects, layout, or scene described by the prompt.<n>Existing supervised emotion-injection methods often optimize feature-space proxies and may therefore exhibit emotion-semantic drift.<n>We address this problem with a flow-matching image-generation framework that combines continuous valence-arousal conditioning, Group Relative Policy Optimization, and a neutral semantic anchor.
  arXiv  Detail & Related papers  (2026-09-11T13:24:35Z)
• Latent-Centroid Steering: Single-Pass Classifier-Free Guidance for Command-Aligned Autonomous Driving [37.533498955258544]
  We propose a single-pass guidance mechanism that replaces instance-level residuals with class-level latent shifts.<n>We demonstrate that LCS reduces inference latency by approximately 50% while achieving stronger command adherence.
  arXiv  Detail & Related papers  (2026-07-31T19:32:28Z)
• PG-MAP: Joint MAP Optimization for Inference-Time Alignment of Diffusion and Flow-Matching Models [0.8594140167290097]
  Inference-time alignment of pretrained text-to-image models is typically performed along a single control axis.<n>We propose PG-MAP, a training-free framework that formulates inference-time alignment as a trajectory-level Gibbs-MAP / proximal energy optimization.
  arXiv  Detail & Related papers  (2026-06-22T07:36:36Z)
• DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding [52.13809682603516]
  DC-Leap is a training-free framework that enables reliable acceleration of dLLMs in the moderate-confidence regime.<n>It incorporates strictly-ordered causal constraints into the parallel decoding process.<n>It achieves substantial speedups, up to 53.19x on MBPP for long-sequence generation, and up to 105.02x when combined with KV-Cache.
  arXiv  Detail & Related papers  (2026-05-19T06:27:58Z)
• AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers [24.937985157569823]
  We argue that such timestep-agnostic alignment is suboptimal because the useful granularity of representation supervision changes systematically with the signal-to-noise ratio.<n>In high-noise regimes, diffusion models benefit more from coarse semantic and layout-level anchoring, whereas in low-noise regimes, the training signal should emphasize spatially detailed and structurally faithful refinement.<n>This non-stationary alignment behavior creates a representational mismatch for static single-level supervisors.
  arXiv  Detail & Related papers  (2026-05-05T03:07:29Z)
• From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons [74.25767873168745]
  Diffusion models promise efficient parallel text generation but rely on bidirectional attention, creating a structural mismatch with pre-trained Autoregressive (AR) models.<n>We propose FLUID, a framework that efficiently adapts AR backbones to the diffusion paradigm.<n> Experiments demonstrate that FLUID achieves state-of-the-art performance while reducing training costs by orders of magnitude.
  arXiv  Detail & Related papers  (2026-04-11T13:18:27Z)
• Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control [33.03635235189535]
  We introduce Generative Control as Optimization (GeCO), a time-unconditional framework that transforms action synthesis into iterative optimization.<n>Test-time inference becomes an adaptive process that allocates computation based on convergence-exiting early for simple states while refining longer for difficult ones.<n>We validate GeCO on standard simulation benchmarks and demonstrate seamless scaling to pi0-series Vision-Language-Action (VLA) models.
  arXiv  Detail & Related papers  (2026-03-18T15:27:17Z)
• OmniVL-Guard: Towards Unified Vision-Language Forgery Detection and Grounding via Balanced RL [63.388513841293616]
  Existing forgery detection methods fail to handle the interleaved text, images, and videos prevalent in real-world misinformation.<n>To bridge this gap, this paper targets to develop a unified framework for omnibus vision-language forgery detection and grounding.<n>We propose textbf OmniVL-Guard, a balanced reinforcement learning framework for omnibus vision-language forgery detection and grounding.
  arXiv  Detail & Related papers  (2026-02-11T09:41:36Z)
• Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping [61.459927600301654]
  Multi-condition control is bottlenecked by the conventional concatenate-and-attend'' strategy.<n>Our analysis reveals that much of this cross-modal interaction is spatially or semantically redundant.<n>We propose Position-aligned and Keyword-scoped Attention (PKA), a highly efficient framework designed to eliminate these redundancies.
  arXiv  Detail & Related papers  (2026-02-06T16:39:10Z)
• Generalized Radius and Integrated Codebook Transforms for Differentiable Vector Quantization [11.898954874548073]
  We introduce a unified surrogate framework that keeps hard assignments in the forward pass while making VQ fully differentiable.<n>GRIT-VQ consistently improves reconstruction error, generative quality, and accuracy compared to existing VQ variants.
  arXiv  Detail & Related papers  (2026-02-01T10:22:35Z)
• Inverse-Free Wilson Loops for Transformers: A Practical Diagnostic for Invariance and Order Sensitivity [0.0]
  WILSON converts simple loop and reordering checks on internal representations into system signals.<n>We present WILSON, a minimal post-hoc diagnostic suite that converts simple loop and reordering checks on internal representations into system signals.
  arXiv  Detail & Related papers  (2025-10-09T06:41:18Z)
• Rectified-CFG++ for Flow Based Models [26.896426878221718]
  We present Rectified-C++, an adaptive predictor-corrector guidance that couples the deterministic efficiency of rectified flows with a geometry-aware conditioning rule.<n>Experiments on large-scale text-to-image models (Flux, Stable Diffusion 3/3.5, Lumina) show that Rectified-C++ consistently outperforms standard CFG on benchmark datasets.
  arXiv  Detail & Related papers  (2025-10-09T00:00:47Z)
• Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval [48.85977777168096]
  Gap-Aware Retrieval framework introduces a learnable, pair-specific increment $Delta_ij$ between text $t_i$ and video $v_j$.<n>A lightweight neural module conditioned on the semantic gap couples increments across batches for structure-aware correction.<n>Experiments on four benchmarks demonstrate that GARE consistently improves alignment accuracy and robustness.
  arXiv  Detail & Related papers  (2025-05-18T17:18:06Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• Adaptive Spot-Guided Transformer for Consistent Local Feature Matching [64.30749838423922]
  We propose Adaptive Spot-Guided Transformer (ASTR) for local feature matching. ASTR models the local consistency and scale variations in a unified coarse-to-fine architecture.
  arXiv  Detail & Related papers  (2023-03-29T12:28:01Z)

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.