Paper page - EchoWM: Open and Enterable Omnimodal World Models

Source: https://huggingface.co/papers/2608.23189 Published on Aug 24

#3 Paper of the day Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

EchoWM is an omnimodal world model that generates synchronized high-resolution video, sound, music, and speech while following continuous 6-DoF navigation trajectories across first- and third-person views.

We present EchoWM, anomnimodal world modelforenterable generative mediathat responds to continuous navigation while jointly generating 720p video, environmental sound, music and speech. We organize interaction aroundcamera 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 relative6-DoF trajectory, withdataset-level calibrationpreserving motion magnitude across heterogeneous data. To jointly learnaudio-visual generationand trajectory control, we construct a complementary data engine and adoptprogressive trainingfollowed byautoregressive post-trainingforlong-horizon generation. Extensive evaluations show that \model achieves strong trajectory following and high visual quality on publicworld-model benchmarks, supporting both first- and third-person interaction across varied subjects, and maintaining synchronized environmental sound and speech overlong-horizon generation.

View arXiv pageView PDFProject pageGitHub1.88kAdd to collection

Get this paper in your agent:

hf papers read 2608\.23189

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.23189 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.23189 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.23189 in a Space README.md to link it from this page.

Collections including this paper1