新AI模型Paris 2.0和Pantheon360推动视频生成技术发展

报道来源 [4]

1. arXiv cs.LG TIER_1 English(EN) · Ali Rouzbayani, Bidhan Roy, Marcos Villagra, Zhiying Jiang · 2026-05-26 04:00

   Paris 2.0: A Decentralized Diffusion Model for Video Generation

   arXiv:2605.26064v1 Announce Type: cross Abstract: 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 open-weight Decentralized Diffusion Model (DDM), wh…

2. arXiv cs.LG TIER_1 English(EN) · Zhiying Jiang · 2026-05-25 17:27

   Paris 2.0: A Decentralized Diffusion Model for Video Generation

   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 open-weight Decentralized Diffusion Model (DDM), which showed that image generation can be trained wi…

3. Hugging Face Daily Papers TIER_1 English(EN) · 2026-05-25 00:00

   Pantheon360: Taming Digital Twin Generation via 3D-Aware 360° Video Diffusion

   Pantheon360 enables high-fidelity 360° video generation for digital twins by combining 3D-aware diffusion with explicit geometric caching to ensure spatial-temporal consistency.

4. arXiv cs.CV TIER_1 English(EN) · Ting-Hsuan Chen, Ying-Huan Chen, Tao Tu, Jie-Ying Lee, Cho-Ying Wu, Fangzhou Lin, Hengyuan Zhang, David Paz, Xinyu Huang, Yuliang Guo, Yu-Lun Liu, Yue Wang, Liu Ren · 2026-05-26 04:00

   Pantheon360: Taming Digital Twin Generation via 3D-Aware 360{\deg} Video Diffusion

   arXiv:2605.25449v1 Announce Type: new Abstract: Generating complete digital twins from videos requires precise camera control, global scene coverage, and strict spatial-temporal consistency constraints that remain challenging for perspective video generators due to their limited …