Related papers: TTSnap: Test-Time Scaling of Diffusion Models via Noise-Aware Pruning

TTSnap: Test-Time Scaling of Diffusion Models via Noise-Aware Pruning

URL: http://arxiv.org/abs/2511.22242v2
Date: Mon, 01 Dec 2025 14:54:43 GMT
Title: TTSnap: Test-Time Scaling of Diffusion Models via Noise-Aware Pruning
Authors: Qingtao Yu, Changlin Song, Minghao Sun, Zhengyang Yu, Vinay Kumar Verma, Soumya Roy, Sumit Negi, Hongdong Li, Dylan Campbell,
Abstract summary: 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.
Score: 53.52543819839442
License: http://creativecommons.org/licenses/by/4.0/
Abstract: A prominent approach to test-time scaling for text-to-image diffusion models formulates the problem as a search over multiple noise seeds, selecting the one that maximizes a certain image-reward function. The effectiveness of this strategy heavily depends on the number and diversity of noise seeds explored. However, verifying each candidate is computationally expensive, because each must be fully denoised before a reward can be computed. This severely limits the number of samples that can be explored under a fixed budget. We propose test-time scaling with noise-aware pruning (TTSnap), a framework that prunes low-quality candidates without fully denoising them. The key challenge is that reward models are learned in the clean image domain, and the ranking of rewards predicted for intermediate estimates are often inconsistent with those predicted for clean images. To overcome this, we train noise-aware reward models via self-distillation to align the reward for intermediate estimates with that of the final clean images. To stabilize learning across different noise levels, we adopt a curriculum training strategy that progressively shifts the data domain from clean images to noise images. In addition, we introduce a new metric that measures reward alignment and computational budget utilization. Experiments demonstrate that our approach improves performance by over 16\% compared with existing methods, enabling more efficient and effective test-time scaling. It also provides orthogonal gains when combined with post-training techniques and local test-time optimization. Code: https://github.com/TerrysLearning/TTSnap/.

Related papers

An Efficient Test-Time Scaling Approach for Image Generation [11.45090928536667]
In particular, searching over noise samples for diffusion and flow models has shown to scale well with test-time compute.<n>We propose the Verifier-Threshold method which automatically reallocates test-time compute.<n>For the same performance on the GenEval benchmark, we achieve a 2-4x reduction in computational time over the state-of-the-art method.
arXiv Detail & Related papers (2025-12-06T09:41:37Z)
Test-Time Scaling of Diffusion Models via Noise Trajectory Search [10.8507840358202]
We introduce an $epsilon$-greedy search algorithm that globally explores at extreme timesteps and locally exploits during the intermediate steps where de-mixing occurs.<n>Experiments on EDM and Stable Diffusion reveal state-of-the-art scores for class-conditioned/text-to-image generation.
arXiv Detail & Related papers (2025-05-24T19:13:29Z)
Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards [52.90573877727541]
reinforcement learning (RL) has been considered for diffusion model fine-tuning.<n>RL's effectiveness is limited by the challenge of sparse reward.<n>$textB2text-DiffuRL$ is compatible with existing optimization algorithms.
arXiv Detail & Related papers (2025-03-14T09:45:19Z)
Robust Representation Consistency Model via Contrastive Denoising [83.47584074390842]
randomized smoothing provides theoretical guarantees for certifying robustness against adversarial perturbations.<n> diffusion models have been successfully employed for randomized smoothing to purify noise-perturbed samples.<n>We reformulate the generative modeling task along the diffusion trajectories in pixel space as a discriminative task in the latent space.
arXiv Detail & Related papers (2025-01-22T18:52:06Z)
Fast constrained sampling in pre-trained diffusion models [80.99262780028015]
We propose an algorithm that enables fast, high-quality generation under arbitrary constraints.<n>Our approach produces results that rival or surpass the state-of-the-art training-free inference methods.
arXiv Detail & Related papers (2024-10-24T14:52:38Z)
An Efficient Rehearsal Scheme for Catastrophic Forgetting Mitigation during Multi-stage Fine-tuning [55.467047686093025]
A common approach to alleviate such forgetting is to rehearse samples from prior tasks during fine-tuning.<n>We propose a sampling scheme, textttbf mix-cd, that prioritizes rehearsal of collateral damage'' samples.<n>Our approach is computationally efficient, easy to implement, and outperforms several leading continual learning methods in compute-constrained settings.
arXiv Detail & Related papers (2024-02-12T22:32:12Z)
Score Priors Guided Deep Variational Inference for Unsupervised Real-World Single Image Denoising [14.486289176696438]
We propose a score priors-guided deep variational inference, namely ScoreDVI, for practical real-world denoising. We exploit a Non-$i.i.d$ Gaussian mixture model and variational noise posterior to model the real-world noise. Our method outperforms other single image-based real-world denoising methods and achieves comparable performance to dataset-based unsupervised methods.
arXiv Detail & Related papers (2023-08-09T03:26:58Z)
Deep Variation Prior: Joint Image Denoising and Noise Variance Estimation without Clean Data [2.3061446605472558]
This paper investigates the tasks of image denoising and noise variance estimation in a single, joint learning framework. We build upon DVP, an unsupervised deep learning framework, that simultaneously learns a denoiser and estimates noise variances. Our method does not require any clean training images or an external step of noise estimation, and instead, approximates the minimum mean squared error denoisers using only a set of noisy images.
arXiv Detail & Related papers (2022-09-19T17:29:32Z)
IDR: Self-Supervised Image Denoising via Iterative Data Refinement [66.5510583957863]
We present a practical unsupervised image denoising method to achieve state-of-the-art denoising performance. Our method only requires single noisy images and a noise model, which is easily accessible in practical raw image denoising. To evaluate raw image denoising performance in real-world applications, we build a high-quality raw image dataset SenseNoise-500 that contains 500 real-life scenes.
arXiv Detail & Related papers (2021-11-29T07:22:53Z)
Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Images [35.41467558264341]
We present a novel approach, called Noise2Score, which reveals a missing link in order to unite different approaches. Specifically, we show that image denoising problems without clean images can be addressed by finding the mode of the posterior distribution. Our method then uses the recent finding that the score function can be stably estimated from the noisy images using the amortized residual denoising autoencoder.
arXiv Detail & Related papers (2021-06-13T14:41:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.