arXiv:2606. 00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models.
By Zhiyuan Feng, Qixiu Li, Huizhi Liang, Rushuai Yang, Yichao Shen, Zhiying Du, Zhaowei Zhang, Yu Deng, Li Zhao, Hao Zhao, Zongqing Lu, Oier Mees, Marc Pollefeys, Jiaolong Yang, Baining Guo
The paper introduces NAVA-WAM, a method that learns action priors directly from observation-only videos to pretrain action policies for robots. It uses a two-stage training process: first, it pretrains on videos with future‑video flow‑matching supervision to learn action‑relevant priors, and second, it fine‑tunes with action‑labeled demonstrations for robot control. Experiments show that NAVA‑WAM outperforms previous methods in both in‑distribution and out‑of‑distribution scenarios, achieving strong action‑label efficiency and real‑robot generalization.
By Zhaochong An, Fei Zhang, Menglin Jia, Duncan Frost, Zijian Zhou, Yikai Wang, Xudong Wang, Aditya Patel, Belinda Zeng, Tao Xiang, Serge Belongie, Amir Bar, Sen He
InternW0-Δ is a unified World Action Model that integrates pretrained visual dynamics, scene semantics, 4D geometry, and motion priors within a Mixture-of-Transformers framework to generate robot actions. It leverages a frozen VLM for semantic guidance, a 4D foundation model for geometric priors, and introduces Causal Imprint to learn future-relevant scene changes without future-video rollout. The model is pretrained on a newly curated 20K‑hour heterogeneous corpus of robot and human demonstrations, achieving superior performance on simulation benchmarks and real‑robot platforms.
By Xingyu Miao, Zizun Li, Baole Fang, Kaiwen Song, Tenghui Wang, Hanxue Zhang, Yating Wang, Xudong Li, Yuping He, Xueyuan Wei, Chao Gao, Xijie Yang, Yingxiang Xu, Kerui Ren, Wenqi Guo, Jianjun Zhou, Xinzhe Wang, Weiguang Zhao, Ni Yang, Zetao Cai, Yufei Xue, Hengjie Li, Zeyu He, Yuanzhen Zhou, Rong Fu, Jianyang Zhang, Siwei Cui, Fuxian Huang, Yunsong Zhou, Xing Gao, Yifei Yao, Qiaojun Yu, Kailin Li, Ming Zhou, Mu Huang, Xinyue Li, Wenze Cui, Bingqi Jiang, Xueyue Zhu, Junting Dong, Haoyu Guo, Tao Lu, Mulin Yu, Bowen Zhou, Bin Zhao, Tianfan Xue, Weinan Zhang, Chunhua Shen
World models enable agents to perform forward rollout and planning without real-world interaction. However, their application in open-world embodied intelligence remains limited by the high cost of action annotations and the heterogeneity of action spaces across platforms.
CLAP is a cross-embodiment framework for action‑conditioned video generation that can be trained on diverse internet‑scale videos from both humans and robots. It reconciles different action spaces—end‑effector poses, language instructions, and latent actions—using a curriculum that first learns physics priors from unlabeled video and then grounds them in real‑world action spaces for zero‑shot deployment. The resulting models match or exceed state‑of‑the‑art single‑embodiment models in challenging environments and support few‑shot adaptation across a wide range of robot morphologies.
By Kechen Liu, Ola Shorinwa
arXiv:2606. 07687v1 Announce Type: cross Abstract: Video world models are increasingly used to provide predictive visual representations, yet it remains unclear which pretraining signals induce action-relevant structure in their latent spaces.
By Jewon Yeom, Hanseul Kim, Jeongjae Park, Sungmok Jung, Jaejin Lee, Taesup Kim
SALA introduces a semantically aligned latent action framework that bridges human and robot video data without requiring paired examples. By leveraging language descriptions to estimate semantic similarities, SALA guides human latent actions toward related robot latents while grounding the latent space with robot action reconstruction. This shared latent action space enables dual‑axis scaling: larger general human pre‑training reduces robot action prediction error, and task‑specific human post‑training boosts real‑world robot success.
By Jiachun Jin, Zetong Zhou, Haonan Wang, Xiao Yang, Jun Zhu, Zhijie Deng
Video Prediction Policy 2 (VPP2) is a new world action model that improves zero‑shot generalization for both video prediction and action generation. It achieves this by pretraining a large, diverse manipulation video dataset with event‑level supervision, then distilling the model into a single‑step visual planner and adding a mixture‑of‑transformers action module. Experiments show VPP2 outperforms leading baselines on open‑ended video prediction, real‑world zero‑shot manipulation, and several challenging benchmarks.
By Yanjiang Guo, Haodong Yan, Zhide Zhong, Zhongru Zhang, Qingyuan Yang, Qingzhou Lu, Xiaoyu Chen, Yen-Jen Wang, Shuying Deng, Chenghan Yang, Puzhen Yuan, Chenxin Liu, Tun Ban, Xiang Zhu, Yichen Liu, Kun Feng, Haoang Li, Jianyu Chen
SALA introduces a method for aligning latent actions across human and robot videos by leveraging language descriptions to create semantic similarities, guiding human latent actions toward related robot latents while grounding the space with robot action reconstruction. This approach avoids the need for paired data and improves training efficiency by preventing visual clustering of latent actions. The shared latent action space enables dual‑axis scaling: larger general human video pre‑training reduces robot action prediction error, and task‑specific human video post‑training boosts real‑world robot task success.
arXiv:2609.19142v1 Announce Type: new
Abstract: World models endow perceptual systems with the ability to predict how scenes evolve under interaction. They are most beneficial when trained on diverse...
By Bardienus P. Duisterhof, Kaifeng Zhang, Adam Hung, Bowen Wen, Stan Birchfield, Yunzhu Li, Deva Ramanan, Jeffrey Ichnowski
arXiv:2609.37250v1 Announce Type: cross
Abstract: World-action models (WAMs) couple future visual-state prediction with action generation. By adapting video generators or image-editing models pretrai...
By Yang Zhang, Jiangyuan Zhao, Chenyou Fan, Jiayu Hu, Xiu Yuan, Chenjia Bai, Xiu Li
OpenNWM is a generalist navigation world model that learns universal latent actions from large-scale action‑free videos and aligns them with physical motions through action‑conditioned post‑training. The authors curate NavAnywhere, a dataset of 17.5 million visual observations from 15 heterogeneous sources, covering diverse viewpoints and motion patterns across five scene types. Experiments show that latent‑action pretraining improves visual prediction and navigation performance both in‑domain and out‑of‑domain.
By Dujun Nie, Ruiqi Song, Zixuan Wang, Hanqing Wang, Yifan Han, Baiyong Ding, Wenzhao Zheng, Hangbin Wu, Long Chen