EchoWM: Open and Enterable Omnimodal World Models
2026-08-24 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created EchoWM, a world model that can generate 720p videos along with matching sounds like environmental noise, music, and speech while letting users move around freely. Their system understands both first-person and third-person views by learning how the camera and characters interact without needing special controls for each view. They convert user commands into a shared space to guide motion consistently, then train their model step-by-step to produce long, coherent audio-visual scenes. Tests show that EchoWM accurately follows movement paths and keeps sound and visuals synchronized over time in different interaction types.
world modelgenerative media6-DoF trajectoryaudio-visual generationfirst-person viewthird-person viewautoregressive trainingenvironmental soundtrajectory controlvideo synthesis
Authors
Songchun Zhang, Yaowei Li, Junhao Zhuang, Weiyang Jin, Haoyu Wang, Xin Lu, Yilang Sun, Shiyi Zhang, Haoran Li, Xiaoxiao Ma, Yuming Li, Yijun Liu, Yaofeng Su, Yanwen Ma, Haoyu Wu, Zihan Su, Yue Ma, Lvmin Zhang, Haoyang Huang, Zeyue Xue, Anyi Rao, Nan Duan
Abstract
We present EchoWM, an omnimodal world model for enterable generative media that responds to continuous navigation while jointly generating 720p video, environmental sound, music and speech. We organize interaction around camera intent: in first-person scenes, it specifies observer motion, while in third-person scenes, camera--character dynamics are learned from data without view-specific controllers. Discrete commands and continuous poses are mapped to a shared metric-scale relative 6-DoF trajectory, with dataset-level calibration preserving motion magnitude across heterogeneous data. To jointly learn audio-visual generation and trajectory control, we construct a complementary data engine and adopt progressive training followed by autoregressive post-training for long-horizon generation. Extensive evaluations show that \model achieves strong trajectory following and high visual quality on public world-model benchmarks, supporting both first- and third-person interaction across varied subjects, and maintaining synchronized environmental sound and speech over long-horizon generation.