Metraipolis › archive › dc_797bdddf7e91

Encore: Infinite Audio-Video Generation with Adaptive Signal Routing — arXiv:2609.04249

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04249
License (as archived)
CC0-1.0
Archived
2026-10-16T23:41:27.570Z
SHA-256 of the archived text
5467bbebdf723f3a6fd94c5c02de990e5fedf621e9cddf267c4790aa07c97f2b
Stable URL of this page
https://metraipolis.com/documento/dc_797bdddf7e91

How to cite

Encore: Infinite Audio-Video Generation with Adaptive Signal Routing — arXiv:2609.04249 — arXiv (en), https://arxiv.org/abs/2609.04249 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_797bdddf7e91 (Metraipolis archive dc_797bdddf7e91, sha256 5467bbebdf723f3a6fd94c5c02de990e5fedf621e9cddf267c4790aa07c97f2b)
BibTeX
@misc{dc797bdddf7e91,
  title = {Encore: Infinite Audio-Video Generation with Adaptive Signal Routing — arXiv:2609.04249},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04249},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_797bdddf7e91; sha256 5467bbebdf723f3a6fd94c5c02de990e5fedf621e9cddf267c4790aa07c97f2b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04249. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing audio-video generation methods produce well-synchronized clips but are limited to short durations, while long-video generation methods extend duration through chunk-based iterative synthesis yet lack audio entirely. Generating long audio-video jointly is fundamentally harder than either task alone: each chunk must simultaneously maintain video temporal coherence, audio temporal coherence, and cross-modal synchronization, whose conditioning signals enter the model through different pathways. In this work, we present Encore for long-form synchronized audio-video generation. Our key insight is to factor this challenge into: (1) local continuity handled by iterative generation with explicit cross-chunk context propagation, and (2) global consistency enforced via reference audio-video signals with shifted position embedding. Building on this design, we propose Adaptive Signal Routing (ASR), which introduces learnable attention biases within self-attention and learnable residual scales on cross-attention outputs, enabling the model to adaptively modulate the influence of each conditioning signal. Trained end-to-end for joint audio-video generation, Encore also supports infinite-length audio-to-video and video-to-audio synthesis at inference by conditioning on the ground-truth modality throughout the denoising process. Experiments on our extended VerseBench for long audio-video evaluation demonstrate that Encore significantly outperforms existing methods in both generation quality and temporal coherence. Code and data for this paper are at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CV).
Categorie arXiv: Multimedia (cs.MM) ; Computer Vision and Pattern Recognition (cs.CV); Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2609.04249 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T23:16:11.470Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).