English(EN)World in World: Explore the World with World Models
新框架推动AI世界模型在模拟和机器人领域的发展 · 跟踪8个来源
作者PulseAugur 编辑部·[8 个来源]·
几篇研究论文介绍了用于推进世界-动作模型的新框架和模型，这对于使AI代理能够理解和与物理世界互动至关重要。World in World 为视频世界模型提供了无需训练的灵活控制接口，而 WorldAgen 则专注于通过测试时训练将这些模型适应新环境。PAN 提出了一个用于通用、可操作和长时域模拟的世界模型架构，ActionSplice 介绍了一种在交互式世界模型中进行飞行中动作编辑的方法。此外，MaP-WAM 通过将规划与执行分离来增强机器人操作能力，OpenWAM 提供了一个开放的、模块化的框架，用于系统化的世界-动作模型预训练。
AI
Autoregressive video world models enable interactive, long-horizon exploration, but flexible control remains challenging. Exploring a source video from new viewpoints requires the generated rollout to remain synchronised with the recorded event, place observed content in the requ…
arXiv:2609.08162v1 Announce Type: new Abstract: How can vision-language-action (VLA) models adapt to new environments where world dynamics shift? While recent research has combined world modeling and action prediction to improve VLA performance, existing methods largely rely on p…
arXiv cs.AI
TIER_1English(EN)·PAN Team, Zihan Liu, Yi Gu, Mingkai Deng, Guangyi Liu, Zeyu Feng, Qiyue Gao, Yiyan Hu, Benhao Huang, Yichi Yang, Kun Zhou, Jiannan Xiang, Zhiting Hu, Zhengzhong Liu, Eric P. Xing·
arXiv:2511.09057v4 Announce Type: replace-cross Abstract: A world model is a cognitive simulator of the real-world environment allowing biological agents to reason about how the world evolves, whether spontaneously or in response to their actions, and accordingly to plan and stra…
arXiv:2609.08230v1 Announce Type: cross Abstract: Chunk-autoregressive video world models typically condition each generated chunk on one action. An action received during sampling must therefore wait for the next chunk, condition future solver evaluations on a state produced und…
A training-free interface enables flexible camera and time control in frozen autoregressive video world models by routing heterogeneous visual evidence through native self-attention with correspondence-guided queries and per-channel attention guidance.
MaP-WAM improves non-Markovian robotic manipulation by separating memory-grounded planning from plan-conditioned execution, using compact episodic segment records and progress-calibrated action chunks to maintain fixed inference latency.
OpenWAM factorizes world-action pretraining into modular components to identify key design principles, yielding a scalable open model with strong simulation and real-robot performance.
arXiv cs.CV
TIER_1English(EN)·Chenxi Song, Yanming Yang, Chi Zhang·
arXiv:2609.11548v1 Announce Type: new Abstract: Autoregressive video world models enable interactive, long-horizon exploration, but flexible control remains challenging. Exploring a source video from new viewpoints requires the generated rollout to remain synchronised with the re…
