Verifier Threshold: An Efficient Test-Time Scaling Approach for Image Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918410278928384 |
|---|---|
| author | Sundaresha, Vignesh Haridas, Akash Appia, Vikram Varshney, Lav R. |
| author_facet | Sundaresha, Vignesh Haridas, Akash Appia, Vikram Varshney, Lav R. |
| contents | Image generation has emerged as a mainstream application of large generative models. Just as test-time compute and reasoning have improved language model capabilities, similar benefits have been observed for image generation models. In particular, searching over noise samples for diffusion and flow models has been shown to scale well with test-time compute. While recent works explore allocating non-uniform inference-compute budgets across denoising steps, existing approaches rely on greedy heuristics and often allocate the compute budget ineffectively. In this work, we study this problem and propose a simple fix. We propose Verifier-Threshold, which automatically reallocates test-time compute and delivers substantial efficiency improvements. For the same performance on the GenEval benchmark, we achieve a 2-4x reduction in computational time over the state-of-the-art method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_08985 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Verifier Threshold: An Efficient Test-Time Scaling Approach for Image Generation Sundaresha, Vignesh Haridas, Akash Appia, Vikram Varshney, Lav R. Computer Vision and Pattern Recognition Image generation has emerged as a mainstream application of large generative models. Just as test-time compute and reasoning have improved language model capabilities, similar benefits have been observed for image generation models. In particular, searching over noise samples for diffusion and flow models has been shown to scale well with test-time compute. While recent works explore allocating non-uniform inference-compute budgets across denoising steps, existing approaches rely on greedy heuristics and often allocate the compute budget ineffectively. In this work, we study this problem and propose a simple fix. We propose Verifier-Threshold, which automatically reallocates test-time compute and delivers substantial efficiency improvements. For the same performance on the GenEval benchmark, we achieve a 2-4x reduction in computational time over the state-of-the-art method. |
| title | Verifier Threshold: An Efficient Test-Time Scaling Approach for Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.08985 |