一个模型同时预测世界状态、生成几何并赋予外观，开启统一3D生成新范式。
arXiv:2608.14530v1 Announce Type: cross Abstract: Interactive game world models typically autoregress visual observations directly in pixel or latent …
一个模型搞定视频理解、生成与编辑，UniVideo重新定义多模态AI边界。
arXiv:2510.08377v4 Announce Type: replace Abstract: Unified multimodal models have shown promising results in multimodal content generation and editin…
提出任务隔离扩散框架，首次统一视频编辑与生成，解决多任务干扰难题。
arXiv:2606.08260v1 Announce Type: new Abstract: Recent advances in Diffusion Transformers have driven rapid progress in video generation and editing, …
首次提出全预训练的统一多模态模型Archon，融合文本、音频、动作与视觉，实现数字人整体生成。
arXiv:2605.30311v1 Announce Type: cross Abstract: Digital humans are fundamental to immersive interaction, yet creating a unified model for holistic m…
一篇探讨从生成图像中反向恢复统一模型的论文，揭秘AIGC隐空间的可逆性。
arXiv:2605.25254v1 Announce Type: cross Abstract: With unified model-generated images now widespread online, attributing their model of origin offers …
统一多模态理解与生成框架，唤醒空间智能，为AI视觉注入全新维度。
arXiv:2605.04128v2 Announce Type: replace-cross Abstract: We present JoyAI-Image, a unified multimodal foundation model for visual understanding, text…
TabH2O统一了表格数据的分类与回归，单模型单次前向传播，基于上下文学习高效预测。
arXiv:2605.18383v1 Announce Type: new Abstract: We present TabH2O, a foundation model for tabular data that performs classification and regression in …
首次实现统一原则训练的具身基础模型，将理解、推理、想象、动作联合优化于单一VLM中，打破独立专家系统架构，性能超越同等规模模型。具身智能迈入真正统一范式。
arXiv:2605.15153v1 Announce Type: cross Abstract: We present Pelican-Unified 1.0, the first embodied foundation model trained according to the princip…