Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.21907 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918515797131264 |
|---|---|
| author | Dai, Gang Huang, Yining Xia, Yiming Chen, Guohao Niu, Shuaicheng |
| author_facet | Dai, Gang Huang, Yining Xia, Yiming Chen, Guohao Niu, Shuaicheng |
| contents | The efficient Test-Time Scaling (TTS) paradigm offers a promising perspective for enhancing the generation performance of diffusion models. However, current solutions are limited to a static, pre-defined noise pool and suffer from inflexible noise exploration across the denoising trajectory. To bridge this gap, we propose RTS, a novel Reward-guided Trajectory Scaling method to fully unlock the generative potential of diffusion models. Unlike existing methods, RTS facilitates the synthesis of refined, high-fidelity images via two core innovations: 1) a reward-guided noise optimization strategy to actively direct the search towards promising regions; and 2) a sparse test-time scaling framework together with a PCA-driven curvature analysis scheme to prioritize key intermediate steps in the entire denoising space, effectively compressing the search space. Experiments show our approach outperforms baselines by 15.6% across GenEval Score, and a 60.4% enhancement in ImageReward score, setting a new SOTA while providing a practical guideline for more effective test-time scaling across diffusion-specific architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_21907 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Guided Trajectory Optimization with Sparse Scaling for Test-Time Diffusion Dai, Gang Huang, Yining Xia, Yiming Chen, Guohao Niu, Shuaicheng Computer Vision and Pattern Recognition The efficient Test-Time Scaling (TTS) paradigm offers a promising perspective for enhancing the generation performance of diffusion models. However, current solutions are limited to a static, pre-defined noise pool and suffer from inflexible noise exploration across the denoising trajectory. To bridge this gap, we propose RTS, a novel Reward-guided Trajectory Scaling method to fully unlock the generative potential of diffusion models. Unlike existing methods, RTS facilitates the synthesis of refined, high-fidelity images via two core innovations: 1) a reward-guided noise optimization strategy to actively direct the search towards promising regions; and 2) a sparse test-time scaling framework together with a PCA-driven curvature analysis scheme to prioritize key intermediate steps in the entire denoising space, effectively compressing the search space. Experiments show our approach outperforms baselines by 15.6% across GenEval Score, and a 60.4% enhancement in ImageReward score, setting a new SOTA while providing a practical guideline for more effective test-time scaling across diffusion-specific architectures. |
| title | Guided Trajectory Optimization with Sparse Scaling for Test-Time Diffusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.21907 |