巴黎：一种去中心化训练的开放权重扩散模型
Paris: A Decentralized Trained Open-Weight Diffusion Model
AI总结：
Paris是一种通过去中心化训练实现高质量文本到图像生成的开放权重扩散模型，无需专用GPU集群，使用更少的数据和计算资源。
摘要：
我们提出了Paris，首个通过去中心化计算完全预训练的扩散模型。Paris证明了无需中心协调基础设施即可实现高质量的文本到图像生成。Paris对研究和商业使用开放。Paris需要从头实现我们的分布式扩散训练框架。该模型由8个专家扩散模型组成（每个模型参数量为129M-605M），在完全隔离的情况下训练，没有梯度、参数或中间激活同步。而不是需要在数千块GPU上同步梯度更新，我们把数据分成语义上连贯的集群，每个专家独立优化其子集，同时集体近似完整分布。一个轻量级的transformer路由器在推理时动态选择合适的专家，生成质量与中心协调的基线相当。消除同步使可以在异构硬件上训练而无需专用互连。实证验证确认Paris的去中心化训练在保持生成质量的同时，消除了大规模扩散模型对专用GPU集群的需求。Paris使用比先前去中心化基线少14倍的训练数据和16倍的计算资源实现了这一点。
英文摘要：
We present Paris, the first publicly released diffusion model pre-trained entirely through decentralized computation. Paris demonstrates that high-quality text-to-image generation can be achieved without centrally coordinated infrastructure. Paris is open for research and commercial use. Paris required implementing our Distributed Diffusion Training framework from scratch. The model consists of 8 expert diffusion models (129M-605M parameters each) trained in complete isolation with no gradient, parameter, or intermediate activation synchronization. Rather than requiring synchronized gradient updates across thousands of GPUs, we partition data into semantically coherent clusters where each expert independently optimizes its subset while collectively approximating the full distribution. A lightweight transformer router dynamically selects appropriate experts at inference, achieving generation quality comparable to centrally coordinated baselines. Eliminating synchronization enables training on heterogeneous hardware without specialized interconnects. Empirical validation confirms that Paris's decentralized training maintains generation quality while removing the dedicated GPU cluster requirement for large-scale diffusion models. Paris achieves this using 14$\times$ less training data and 16$\times$ less compute than the prior decentralized baseline.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
