English
Related papers

Related papers: EA-WM: Event-Aware Generative World Model with Str…

200 papers

While video-generation-based embodied world models have gained increasing attention, their reliance on large-scale embodied interaction data remains a key bottleneck. The scarcity, difficulty of collection, and high dimensionality of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Hao Li , Qiao Sun

This work highlights that video world modeling, alongside vision-language pre-training, establishes a fresh and independent foundation for robot learning. Intuitively, video world models provide the ability to imagine the near future by…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Lin Li , Qihang Zhang , Yiming Luo , Shuai Yang , Ruilin Wang , Fei Han , Mingrui Yu , Zelin Gao , Nan Xue , Xing Zhu , Yujun Shen , Yinghao Xu

World models have become a central paradigm for learning predictive simulators that support generation, planning, and decision-making. Yet, despite rapid progress in industry-scale interactive video generation, the broader research…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Siqiao Huang , Partha Kaushik , Michael Chen , Hengkai Pan , Kaiwen Geng , Omar Chehab , Fernando Moreno-Pino , Max Simchowitz

The vision-language-action (VLA) paradigm has enabled powerful robotic control by leveraging vision-language models, but its reliance on large-scale, high-quality robot data limits its generalization. Generative world models offer a…

Robotics · Computer Science 2026-01-27 Weishi Mi , Yong Bao , Xiaowei Chi , Xiaozhu Ju , Zhiyuan Qin , Kuangzhi Ge , Kai Tang , Peidong Jia , Shanghang Zhang , Jian Tang

Recent video diffusion foundation models have achieved remarkable progress in high-quality video generation, yet turning them into real-time interactive video world models remains challenging. Interactive world models require controllable,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Min Zhao , Hongzhou Zhu , Bokai Yan , Zihan Zhou , Yimin Chen , Wenqiang Sun , Kaiwen Zheng , Guande He , Xiao Yang , Chongxuan Li , Fan Bao , Jun Zhu

World-Action Models (WAM) initialized from pre-trained video generation backbones have demonstrated remarkable potential for robot policy learning. However, existing approaches face two critical bottlenecks that hinder performance and…

Foundation video models produce visually impressive results, but their use in embodied AI remains limited because they are primarily trained on natural language rather than low-level control signals. This limitation is especially pronounced…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Abdul Mohaimen Al Radi , Kunyang Li , Yuzhang Shang , Mubarak Shah , Yu Tian

Predictive manipulation has recently gained considerable attention in the Embodied AI community due to its potential to improve robot policy performance by leveraging predicted states. However, generating accurate future visual states of…

Robotics · Computer Science 2025-09-15 Yuhang Huang , Jiazhao Zhang , Shilong Zou , Xinwang Liu , Ruizhen Hu , Kai Xu

Simulating robot-world interactions is a cornerstone of Embodied AI. Recently, a few works have shown promise in leveraging video generations to transcend the rigid visual/physical constraints of traditional simulators. However, they…

Robotics · Computer Science 2026-03-18 Mutian Xu , Tianbao Zhang , Tianqi Liu , Zhaoxi Chen , Xiaoguang Han , Ziwei Liu

World models derived from large-scale video generative pre-training have emerged as a promising paradigm for generalist robot policy learning. However, standard approaches often focus on high-fidelity RGB video prediction, this can result…

Recent advances in robot foundation models trained on large-scale human teleoperation data have enabled robots to perform increasingly complex real-world tasks. However, scaling these systems remains difficult because collecting…

Action-conditioned world models (ACWMs) have shown strong promise for video prediction and decision-making. However, existing benchmarks are largely restricted to egocentric navigation or narrow, task-specific robotics datasets, offering…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Haotian Xue , Yipu Chen , Liqian Ma , Zelin Zhao , Lama Moukheiber , Yuchen Zhu , Yongxin Chen

Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from perception to action,…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Haoyu Zhen , Xiaowen Qiu , Peihao Chen , Jincheng Yang , Xin Yan , Yilun Du , Yining Hong , Chuang Gan

Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning, yet they learn reactive observation-to-action mappings without explicitly modeling how the physical world evolves under…

State-of-the-art Vision-Language-Action (VLA) models excel at semantic generalization but struggle to generalize to unseen physical motions in novel environments. We introduce DreamZero, a World Action Model (WAM) built upon a pretrained…

Humans develop an understanding of intuitive physics through active interaction with the world. This approach is in stark contrast to current video models, such as Sora, which rely on passive observation and therefore struggle with grasping…

Robotic world models are a promising paradigm for forecasting future environment states, yet their inference speed and the physical plausibility of generated trajectories remain critical bottlenecks, limiting their real-world applications.…

Robotics · Computer Science 2025-09-26 Sibo Li , Qianyue Hao , Yu Shang , Yong Li

Robotic manipulation requires anticipating how the environment evolves in response to actions, yet most existing systems lack this predictive capability, often resulting in errors and inefficiency. While Vision-Language Models (VLMs)…

Robotics · Computer Science 2026-02-12 Songen Gu , Yunuo Cai , Tianyu Wang , Simo Wu , Yanwei Fu

World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics. Current WAMs generally follow two paradigms: the "Imagine-then-Execute" approach, which uses video prediction to infer actions…

Autonomous agents operating in dynamic and safety-critical environments require decision-making frameworks that are both computationally efficient and physically grounded. However, many existing approaches rely on end-to-end learning, which…

Machine Learning · Computer Science 2026-05-01 Zhaowen Fan , Rongchao Zhang