近期研究探索了扩散模型（一种主流的图像生成架构）的进展。一篇论文揭示了这些模型固有地利用了类似于Transformer的注意力机制，这表明注意力是一种通用的机器学习原理。另一项研究引入了控制变量分数匹配（CVSI）来提高扩散模型的采样效率并降低方差。此外，一种名为优势加权匹配（AWM）的新方法将强化学习目标与扩散模型的预训练相结合，从而显著加快了生成质量。
AI
arXiv:2609.04090v1 Announce Type: new Abstract: Current conditioned generative models heavily rely on score functions for guidance during training. When the generative model is a diffusion process with a singular diffusion coefficient and the underlying (conditional) densities ei…
arXiv:2506.10226v3 Announce Type: replace-cross Abstract: Synthetic data generation is increasingly used in machine learning for training and data augmentation. Yet, current strategies often rely on external foundation models or datasets, whose usage is restricted in many scenari…
Current conditioned generative models heavily rely on score functions for guidance during training. When the generative model is a diffusion process with a singular diffusion coefficient and the underlying (conditional) densities either do not exist or are not smooth, we use caus…
arXiv cs.LG
TIER_1English(EN)·Patrick Reichherzer, Gianluca Gregori, David N. Hosking, Subir Sarkar·
arXiv:2609.01705v1 Announce Type: new Abstract: Stochastic transport describes physical systems in which an initially structured distribution spreads under unresolved forcing, scattering, or heterogeneous media. Useful surrogates for such systems should be probabilistic, time-res…
arXiv:2511.03913v3 Announce Type: replace-cross Abstract: Deep diffusion models have revolutionized image generation by producing high-quality outputs. However, achieving specific objectives with these models often requires costly adaptations such as fine-tuning, which can be res…
arXiv cs.LG
TIER_1English(EN)·Khaled Kahouli, Romuald Elie, Klaus-Robert M\"uller, Quentin Berthet, Oliver T. Unke, Arnaud Doucet·
arXiv:2512.20003v2 Announce Type: replace Abstract: Sampling from unnormalized probability densities is a pervasive challenge across the computational and physical sciences. Diffusion models provide a powerful generative framework for this task, but their success relies on accura…
arXiv:2609.00885v1 Announce Type: new Abstract: Denoising diffusion models are the dominant architecture for image generation, whereas most natural language generation and modeling are primarily handled by well-known transformer architectures employing attention mechanism. Here, …
arXiv:2509.25050v2 Announce Type: replace Abstract: Reinforcement Learning (RL) has emerged as a central paradigm for advancing Large Language Models (LLMs), where both pre-training and RL post-training stages are grounded in the same log-likelihood formulation. In contrast, rece…
Denoising diffusion models are the dominant architecture for image generation, whereas most natural language generation and modeling are primarily handled by well-known transformer architectures employing attention mechanism. Here, we show that diffusion models also inherently us…
arXiv:2206.09012v4 Announce Type: replace Abstract: We consider the problem of inferring high-dimensional data $\mathbf{x}$ in a model that consists of a prior $p(\mathbf{x})$ and an auxiliary differentiable constraint $c(\mathbf{x},\mathbf{y})$ on $x$ given some additional infor…
arXiv cs.LG
TIER_1English(EN)·Siddarth Venkatraman, Moksh Jain, Luca Scimeca, Minsu Kim, Marcin Sendera, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yoshua Bengio, Glen Berseth, Esmeralda S. Whitammer·
arXiv:2405.20971v3 Announce Type: replace Abstract: Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors in downstream tasks poses an intractable posterior inference problem. This paper studies…
arXiv:2609.01166v1 Announce Type: cross Abstract: The present research is devoted to the nonparametric estimation of a density-dependent drift coefficient in a multivariate McKean--Vlasov diffusion from independent observations at a common time, as well as the stationary density.…
