CARINOX: Inference-time Scaling with Category-Aware Reward-based Initial Noise Optimization and Exploration

• URL: http://arxiv.org/abs/2509.17458v1
• Date: Mon, 22 Sep 2025 07:51:28 GMT
• Title: CARINOX: Inference-time Scaling with Category-Aware Reward-based Initial Noise Optimization and Exploration
• Abstract summary: Category-Aware Reward-based Initial Noise Optimization and Exploration (CARINOX)<n>We present Category-Aware Reward-based Initial Noise Optimization and Exploration (CARINOX)<n>We show that CARINOX raises average alignment scores by +16% on T2I-CompBench++ and +11% on the HRS benchmark.
• Score: 12.905084796136883
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-image diffusion models, such as Stable Diffusion, can produce high-quality and diverse images but often fail to achieve compositional alignment, particularly when prompts describe complex object relationships, attributes, or spatial arrangements. Recent inference-time approaches address this by optimizing or exploring the initial noise under the guidance of reward functions that score text-image alignment without requiring model fine-tuning. While promising, each strategy has intrinsic limitations when used alone: optimization can stall due to poor initialization or unfavorable search trajectories, whereas exploration may require a prohibitively large number of samples to locate a satisfactory output. Our analysis further shows that neither single reward metrics nor ad-hoc combinations reliably capture all aspects of compositionality, leading to weak or inconsistent guidance. To overcome these challenges, we present Category-Aware Reward-based Initial Noise Optimization and Exploration (CARINOX), a unified framework that combines noise optimization and exploration with a principled reward selection procedure grounded in correlation with human judgments. Evaluations on two complementary benchmarks covering diverse compositional challenges show that CARINOX raises average alignment scores by +16% on T2I-CompBench++ and +11% on the HRS benchmark, consistently outperforming state-of-the-art optimization and exploration-based methods across all major categories, while preserving image quality and diversity. The project page is available at https://amirkasaei.com/carinox/{this URL}.

Related papers

• DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment [49.45064510462232]
  GRPO-based approaches for text-to-image generation suffer from the sparse reward problem.<n>We introduce textbfDenseGRPO, a novel framework that aligns human preference with dense rewards.
  arXiv  Detail & Related papers  (2026-01-28T03:39:05Z)
• Neural Nonmyopic Bayesian Optimization in Dynamic Cost Settings [73.44599934855067]
  LookaHES is a nonmyopic BO framework designed for dynamic, history-dependent cost environments.<n>LookaHES combines a multi-step variant of $H$-Entropy Search with pathwise sampling and neural policy optimization.<n>Our innovation is the integration of neural policies, including large language models, to effectively navigate structured, domain-specific action spaces.
  arXiv  Detail & Related papers  (2026-01-10T09:49:45Z)
• It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models [80.53672733210111]
  We show that a simple noise optimization objective can mitigate mode collapse while preserving the fidelity of the base model.<n>Our experiments demonstrate that noise optimization yields superior results in terms of generation quality and variety.
  arXiv  Detail & Related papers  (2025-12-31T19:47:49Z)
• TTSnap: Test-Time Scaling of Diffusion Models via Noise-Aware Pruning [53.52543819839442]
  A prominent approach to test-time scaling for text-to-image diffusion models formulates the problem as a search over multiple noise seeds.<n>We propose test-time scaling with noise-aware pruning (TTSnap), a framework that prunes low-quality candidates without fully denoising them.
  arXiv  Detail & Related papers  (2025-11-27T09:14:26Z)
• Beyond Frequency: Scoring-Driven Debiasing for Object Detection via Blueprint-Prompted Image Synthesis [97.37770785712475]
  We present a generation-based debiasing framework for object detection.<n>Our method significantly narrows the performance gap for underrepresented object groups.
  arXiv  Detail & Related papers  (2025-10-21T02:19:12Z)
• Saccadic Vision for Fine-Grained Visual Classification [10.681604440788854]
  Fine-grained visual classification (FGVC) requires distinguishing between visually similar categories through subtle, localized features.<n>Existing part-based methods rely on complex localization networks that learn mappings from pixel to sample space.<n>We propose a two-stage process that first extracts peripheral features and generates a sample map.<n>We employ contextualized selective attention to weigh the impact of each fixation patch before fusing peripheral and focus representations.
  arXiv  Detail & Related papers  (2025-09-19T07:03:37Z)
• OptiPrune: Boosting Prompt-Image Consistency with Attention-Guided Noise and Dynamic Token Selection [0.0]
  We propose a unified framework that combines distribution-aware initial noise optimization with similarity-based token pruning.<n>Experiments on benchmark datasets, including Animal-Animal, demonstrate that OptiPrune achieves state-of-the-art prompt-image consistency with significantly reduced computational cost.
  arXiv  Detail & Related papers  (2025-07-01T14:24:40Z)
• Reward-Agnostic Prompt Optimization for Text-to-Image Diffusion Models [13.428939931403473]
  We introduce RATTPO, a flexible test-time optimization method applicable across various reward scenarios without modification.<n>RATTPO searches for optimized prompts by querying large language models (LLMs) textitwithout requiring reward-specific task descriptions.<n> Empirical results demonstrate the versatility of RATTPO, effectively enhancing user prompts across diverse reward setups.
  arXiv  Detail & Related papers  (2025-06-20T09:02:05Z)
• A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsampling [54.05517338122698]
  A popular similarity-based feature upsampling pipeline has been proposed, which utilizes a high-resolution feature as guidance.<n>We propose an explicitly controllable query-key feature alignment from both semantic-aware and detail-aware perspectives.<n>We develop a fine-grained neighbor selection strategy on HR features, which is simple yet effective for alleviating mosaic artifacts.
  arXiv  Detail & Related papers  (2024-07-02T14:12:21Z)
• Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction [31.503662384666274]
  In science and engineering, the goal is to infer an unknown image from a small number of measurements collected from a known forward model describing certain imaging modality. Motivated Score-based diffusion models, due to its empirical success, have emerged as an impressive candidate of an exemplary prior in image reconstruction.
  arXiv  Detail & Related papers  (2024-03-25T15:58:26Z)
• High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise [96.80184504268593]
  gradient, clipping is one of the key algorithmic ingredients to derive good high-probability guarantees. Clipping can spoil the convergence of the popular methods for composite and distributed optimization.
  arXiv  Detail & Related papers  (2023-10-03T07:49:17Z)
• Advancing Unsupervised Low-light Image Enhancement: Noise Estimation, Illumination Interpolation, and Self-Regulation [55.07472635587852]
  Low-Light Image Enhancement (LLIE) techniques have made notable advancements in preserving image details and enhancing contrast. These approaches encounter persistent challenges in efficiently mitigating dynamic noise and accommodating diverse low-light scenarios. We first propose a method for estimating the noise level in low light images in a quick and accurate way. We then devise a Learnable Illumination Interpolator (LII) to satisfy general constraints between illumination and input.
  arXiv  Detail & Related papers  (2023-05-17T13:56:48Z)
• A Unified Framework of Bundle Adjustment and Feature Matching for High-Resolution Satellite Images [4.835738511987696]
  This article incorpo-rates Bundle adjustment (BA) and feature matching in a unified framework. Experiments on multi-view high-resolution satellite images show that our proposed method outperforms state-of-the-art orientation techniques.
  arXiv  Detail & Related papers  (2021-07-01T16:40:25Z)
• Learning to Estimate Hidden Motions with Global Motion Aggregation [71.12650817490318]
  Occlusions pose a significant challenge to optical flow algorithms that rely on local evidences. We introduce a global motion aggregation module to find long-range dependencies between pixels in the first image. We demonstrate that the optical flow estimates in the occluded regions can be significantly improved without damaging the performance in non-occluded regions.
  arXiv  Detail & Related papers  (2021-04-06T10:32:03Z)
• Spatial-spectral Hyperspectral Image Classification via Multiple Random Anchor Graphs Ensemble Learning [88.60285937702304]
  This paper proposes a novel spatial-spectral HSI classification method via multiple random anchor graphs ensemble learning (RAGE) Firstly, the local binary pattern is adopted to extract the more descriptive features on each selected band, which preserves local structures and subtle changes of a region. Secondly, the adaptive neighbors assignment is introduced in the construction of anchor graph, to reduce the computational complexity.
  arXiv  Detail & Related papers  (2021-03-25T09:31:41Z)

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.