Research map / Video / Video generation
WorldForge: Forging Unified World Modeling into Video Generation
Boming Tan, Xiangdong Zhang, Ning Liao, Jingtao Zhang, 张雨晴, Xiaoqiu Zhong, Xiaosong Jia, Xue Yang, Shaofeng Zhang, Yanyong Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
WorldForge proposes a unified world-modeling approach for video generation that aims to integrate multiple forms of world knowledge rather than a single one or rigid alignment.
Problem
Existing video generation models produce surface-level plausibility and lack a coherent, unified understanding of the world; prior methods inject only one form of world knowledge or rely on rigid alignment strategies.
Approach
Argues that aligning a single world-knowledge source is insufficient for a world model and instead unifies multiple world-related knowledge forms into video generation, in contrast to prior single-knowledge or rigid-alignment approaches.
Closest papers by meaning
- WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception (NeurIPS 2025 · similarity 0.90)
- Video World Models with Long-term Spatial Memory (NeurIPS 2025 · similarity 0.89)
- Learning World Models for Interactive Video Generation (NeurIPS 2025 · similarity 0.89)
- WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors (NeurIPS 2026 · similarity 0.89)
- WorldModelBench: Judging Video Generation Models As World Models (NeurIPS 2025 · similarity 0.89)
- Trimming the Long-Tail of Visual World Modeling Evaluation (NeurIPS 2026 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
