One step further with Monte-Carlo sampler to guide diffusion better
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918376202305536 |
|---|---|
| author | Ren, Minsi Deng, Wenhao Feng, Ruiqi Wu, Tailin |
| author_facet | Ren, Minsi Deng, Wenhao Feng, Ruiqi Wu, Tailin |
| contents | Stochastic differential equation (SDE)-based generative models have achieved substantial progress in conditional generation via training-free differentiable loss-guided approaches. However, existing methodologies utilizing posterior sam- pling typically confront a substantial estimation error, which results in inaccu- rate gradients for guidance and leading to inconsistent generation results. To mitigate this issue, we propose that performing an additional backward denois- ing step and Monte-Carlo sampling (ABMS) can achieve better guided diffu- sion, which is a plug-and-play adjustment strategy. To verify the effectiveness of our method, we provide theoretical analysis and propose the adoption of a dual-focus evaluation framework, which further serves to highlight the critical problem of cross-condition interference prevalent in existing approaches. We conduct experiments across various task settings and data types, mainly includ- ing conditional online handwritten trajectory generation, image inverse problems (inpainting, super resolution and gaussian deblurring) molecular inverse design and so on. Experimental results demonstrate that our approach can be effec- tively used with higher order samplers and consistently improves the quality of generation samples across all the different scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_06685 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | One step further with Monte-Carlo sampler to guide diffusion better Ren, Minsi Deng, Wenhao Feng, Ruiqi Wu, Tailin Machine Learning Stochastic differential equation (SDE)-based generative models have achieved substantial progress in conditional generation via training-free differentiable loss-guided approaches. However, existing methodologies utilizing posterior sam- pling typically confront a substantial estimation error, which results in inaccu- rate gradients for guidance and leading to inconsistent generation results. To mitigate this issue, we propose that performing an additional backward denois- ing step and Monte-Carlo sampling (ABMS) can achieve better guided diffu- sion, which is a plug-and-play adjustment strategy. To verify the effectiveness of our method, we provide theoretical analysis and propose the adoption of a dual-focus evaluation framework, which further serves to highlight the critical problem of cross-condition interference prevalent in existing approaches. We conduct experiments across various task settings and data types, mainly includ- ing conditional online handwritten trajectory generation, image inverse problems (inpainting, super resolution and gaussian deblurring) molecular inverse design and so on. Experimental results demonstrate that our approach can be effec- tively used with higher order samplers and consistently improves the quality of generation samples across all the different scenarios. |
| title | One step further with Monte-Carlo sampler to guide diffusion better |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2603.06685 |