Awesome World Models / arXiv

WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens

作者：作者信息待提取 · 单位：Tsinghua University · 来源：General Approaches to World Models · 发布日期：2024 · 分类：2. Building World Models from 2D Vision Priors / Pixel Space World Models

二维视觉先验基于模型的强化学习视频生成
新标签打开 AlphaXiv新标签打开 Code
WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens figure
AlphaXiv 中文概览（可滚动查看）