# SITA：可扩展的推理时间退火方法

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-01 08:00
- AIHOT 分数：46
- AIHOT 链接：https://aihot.virxact.com/items/cmpzsaqxj06hgslkp1oh9qgys
- 原文链接：https://arxiv.org/abs/2605.31498

## AI 摘要

计算化学和生物物理中长期挑战是高效采样分子玻尔兹曼分布。现有方法通过迭代微调扩散模型沿温度梯度进行推理时间退火，但需计算分数场散度来估计重要性权重，对大系统不可行。本文提出可扩展推理时间退火（SITA），利用能量模型提供快速替代似然，重新训练基于流的模型逐步降低温度生成样本。在Alanine Dipeptide和Alanine Tripeptide上达到最先进性能，避免了昂贵的散度项。代码已开源。

## 正文

A long standing challenge in computational chemistry and biophysics is efficiently sampling the Boltzmann distribution of molecules. Advances in generative modeling have been proposed to address the limitations of conventional sampling techniques by eliminating the computational cost of simulation. A promising direction is iteratively finetuning diffusion models along a temperature ladder whereby training data is generated via importance sampling during inference-time annealing. Unfortunately, these methods require computing a divergence over the score field to estimate importance weights, rendering them intractable for larger systems. Here we present scalable inference-time annealing (SITA), which retrains flow-based models to generate samples at progressively lower temperatures using an energy-based model to facilitate fast surrogate likelihoods. We demonstrate state-of-the-art performance on both Alanine Dipeptide and Alanine Tripeptide while avoiding costly divergence terms. Our code is available at https://github.com/countrsignal/sita.git