5 papers
WorldDiT: A Unified Diffusion Architecture for World and Action Modeling
Sen Wang, R. Gnana Praveen, Bidhan Roy +1
Many recent robot policies pursue stronger control by using large pretrained vision-language models (VLMs) as the action backbone. We introduce WorldDiT, a unified diffusion transf…
Heterogeneous Decentralized Diffusion Models
Zhiying Jiang, Raihan Seraj, Marcos Villagra +1
Training frontier-scale diffusion models often requires substantial computational resources concentrated in tightly-coupled clusters, limiting participation to well-resourced insti…
Paris 2.0: A Decentralized Diffusion Model for Video Generation
Ali Rouzbayani, Bidhan Roy, Marcos Villagra +1
We present Paris 2.0, the first video generation model pre-trained through decentralized computation. Its training recipe builds upon Paris 1.0 (arXiv:2510.03434), the first ever o…
Expert-Data Alignment Governs Generation Quality in Decentralized Diffusion Models
Marcos Villagra, Bidhan Roy, Raihan Seraj +1
Decentralized Diffusion Models (DDMs) route denoising through experts trained independently on disjoint data clusters, which can strongly disagree in their predictions. What govern…
Paris: A Decentralized Trained Open-Weight Diffusion Model
Zhiying Jiang, Raihan Seraj, Marcos Villagra +1
We present Paris, the first publicly released diffusion model pre-trained entirely through decentralized computation. Paris demonstrates that high-quality text-to-image generation…