Paper page - Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds

Source: https://huggingface.co/papers/2608.23383 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

JoyAI-Echo-1.5 unifies long-form video and interactive world generation through cross-shot memory, geometry-aware camera control, and rollout-aware training to maintain identity and coherence over extended sequences.

Video generation is progressing beyond isolated clips toward long-form narratives and interactive worlds, requiring models to preserve identities, follow user controls, and remain stable over extended rollouts. We present JoyAI-Echo-1.5, a unified audio-visual generation system with two purpose-built variants. The long-video variant introduces composablecross-shot memorythat aggregates visual evidence across multiple prior shots andspeaker cuesderived from speech-filtered full-shot audio, enabling persistent character appearance and voice identity across flexible combinations of text, image, and memory conditioning. The world-model variant converts heterogeneous navigation inputs into calibrated metric6-DoF camera trajectoriesand injects them through ageometry-aware conditioningpathway, enabling controller-agnostic interaction across flexible viewpoints. To support efficient long-horizon generation, we transform abidirectional audio-visual backboneinto acausal few-step generatorusingprogressive teacher forcingand short- and long-horizonSelf-Gradient Forcingonself-generated rollouts. Experiments demonstrate strong performance in both settings. JoyAI-Echo-1.5 achieves improvements over existing long-video baselines in cross-shot consistency, visual quality, text alignment, and speech fidelity. Its world-model variant ranks first on WBench, with an average score of 81.7, and achieves leading visual quality and long-horizon persistence on SANA-WM-Bench. Together, these results indicate that memory, geometric control, and rollout-aware training provide a practical foundation for generating coherent stories and continuously evolving interactive worlds. Project page: https://echo-team-joy-future-academy-jd.github.io/Echo-1.5-Page/.

View arXiv pageView PDFProject pageGitHub1.95kAdd to collection

Get this paper in your agent:

hf papers read 2608\.23383

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/2608.23383 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.23383 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.23383 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.