← 研踪 PaperTrailarXiv:2606.24152 · v3
Autonomous Video Generation for Self-Evolving World Models
首次提交 2026-06-23 13:19
版本更新 2026-11-18 18:08
雷达观测 2026-11-19 15:04
摘要
Large-scale video generation models are increasingly described as world models because they can learn rich spatiotemporal regularities from visual data. We argue that an ideal world model should benefit in a self-evolving generative character. As such, a self-evolving world model can be realized via a generative model conditioned by various constraints, whose future predictions are refined through feedback. However, traditional visually plausible predictions alone are not enough to establish whether an imagined future is physically actionable for a particular embodied agent, failing to provide informative feedback from environments for self-evolving improvement. To realize self-evolving world models, this article proposes the concept of autonomous video generation, which is evaluated through counterfactual controllability, i.e., the ability to i) generate intervention-conditioned futures, ii) bind these future frames to embodiment constraints, iii) verify them under distribution shifts, and iv) distil surviving branches into compact variables for decision-making. We formalize a four-stage closed-loop optimization of Generation, Binding, Verification and Distillation, together with four corresponding evaluation metrics: novelty, consistency, out-of-distribution (OOD) and efficiency. We further discuss two examples, i.e., drones and manipulators, as early embodied testbeds where wind, sensing limits, actuation delay, contact dynamics and recovery constraints can be systematically perturbed and verified. The central claim is that the framework of autonomous video generation for self-evolving world models should not be judged by video fidelity alone, but by whether the generated frames improve valid action under counterfactual interventions and various embodiment constraints.
作者备注:7 pages, 2 figures; To appear in ENGINEERING Artificial Intelligence (https://journal.hep.com.cn/eai/EN/)
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v3 · 2026-11-18 18:08 · 最新观测版本
Autonomous Video Generation for Self-Evolving World Models
Large-scale video generation models are increasingly described as world models because they can learn rich spatiotemporal regularities from visual data. We argue that an ideal world model should benefit in a self-evolving generative character. As such, a self-evolving world model can be realized via a generative model conditioned by various constraints, whose future predictions are refined through feedback. However, traditional visually plausible predictions alone are not enough to establish whether an imagined future is physically actionable for a particular embodied agent, failing to provide informative feedback from environments for self-evolving improvement. To realize self-evolving world models, this article proposes the concept of autonomous video generation, which is evaluated through counterfactual controllability, i.e., the ability to i) generate intervention-conditioned futures, ii) bind these future frames to embodiment constraints, iii) verify them under distribution shifts, and iv) distil surviving branches into compact variables for decision-making. We formalize a four-stage closed-loop optimization of Generation, Binding, Verification and Distillation, together with four corresponding evaluation metrics: novelty, consistency, out-of-distribution (OOD) and efficiency. We further discuss two examples, i.e., drones and manipulators, as early embodied testbeds where wind, sensing limits, actuation delay, contact dynamics and recovery constraints can be systematically perturbed and verified. The central claim is that the framework of autonomous video generation for self-evolving world models should not be judged by video fidelity alone, but by whether the generated frames improve valid action under counterfactual interventions and various embodiment constraints.
查看此版本解读 →查看此版本原文 ↗