🛰️ Daily AI Frontier
‹ back to 2026-09-23

Code Plans, Diffusion Renders: Open-Ended Generative World Modeling

Research Multimodal & Generative

Ranking

Overall 75
Content 95
Popularity 29

Observed public metrics from 1 member.

Representative image for Code Plans, Diffusion Renders: Open-Ended Generative World Modeling

Merged summary

TL;DR - CoDeR is a generative world-modeling framework that encodes world rules and dynamics as executable code, then uses video generation models to render visual observations. This separation aims to support persistent, open-ended simulations beyond the temporal limits of conventional video world models.

  • Coordinates five complementary roles to translate high-level concepts into structured rules, executable dynamics, and perceptual outputs.
  • Maintains explicit state for long-term memory, autonomous world evolution, and interactions extending beyond the current observation.
  • Supports persistent multi-agent scenarios in which multiple entities can act, interact, and evolve.
  • The authors report state-of-the-art results across multiple evaluation settings and plan to release code and model weights.

Sources (1)

Code Plans, Diffusion Renders: Open-Ended Generative World Modeling

arXiv cs.CV Zixun Fang, Yawen Shao, Kai Zhu, Jie Xiao, Shihan Chen, Yu Liu, Xueyang Fu, Yang Cao, Wei Zhai, Zheng-Jun Zha 2026-09-22 arXiv:2609.26458
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-09-24 14:15:51.424693 UTC

TL;DR - CoDeR is a generative world-modeling framework that encodes world rules and dynamics as executable code, then uses video generation models to render visual observations. This separation aims to support persistent, open-ended simulations beyond the temporal limits of conventional video world models.

  • Coordinates five complementary roles to translate high-level concepts into structured rules, executable dynamics, and perceptual outputs.
  • Maintains explicit state for long-term memory, autonomous world evolution, and interactions extending beyond the current observation.
  • Supports persistent multi-agent scenarios in which multiple entities can act, interact, and evolve.
  • The authors report state-of-the-art results across multiple evaluation settings and plan to release code and model weights.
item →