Metraipolis › archive › dc_eea94033c730

Efficient Multimodal Generative Recommendation with Latent Narrative Reasoning — arXiv:2609.16070

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16070
License (as archived)
CC0-1.0
Archived
2026-10-15T18:32:36.244Z
SHA-256 of the archived text
5709b4d4ef6637eeb98e2958e7ae5311f4afa1596750a028a679fa0f1b864f5d
Stable URL of this page
https://metraipolis.com/documento/dc_eea94033c730

How to cite

Efficient Multimodal Generative Recommendation with Latent Narrative Reasoning — arXiv:2609.16070 — arXiv (en), https://arxiv.org/abs/2609.16070 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eea94033c730 (Metraipolis archive dc_eea94033c730, sha256 5709b4d4ef6637eeb98e2958e7ae5311f4afa1596750a028a679fa0f1b864f5d)
BibTeX
@misc{dceea94033c730,
  title = {Efficient Multimodal Generative Recommendation with Latent Narrative Reasoning — arXiv:2609.16070},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16070},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eea94033c730; sha256 5709b4d4ef6637eeb98e2958e7ae5311f4afa1596750a028a679fa0f1b864f5d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16070. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative recommendation reformulates item prediction as semantic identifier generation, yet episodic content introduces a fundamentally different setting where the target is determined by narrative evolution rather than user preference. This task requires models to understand multimodal storyline progression while addressing the efficiency challenges caused by redundant visual contexts and costly explicit reasoning generation. We propose \textbf{NarraLite}, an efficient multimodal generative recommendation framework that jointly compresses perception and reasoning. Specifically, Progressive Spectral Compression selectively distills long visual contexts into compact narrative-relevant evidence, preserving transition-critical information while reducing redundant visual computation. Latent Narrative Reasoning introduces context-routed latent reasoning tokens and aligns their contextualized representations with future continuation semantics, enabling implicit narrative inference without autoregressively decoding textual rationales. We further establish a user-agnostic multimodal benchmark for short-form drama continuation across UGC, PGC, and OOD settings. Extensive experiments demonstrate that NarraLite consistently improves continuation accuracy, narrative coherence, and robustness over existing approaches, while achieving a favorable accuracy--efficiency trade-off.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.16070 — 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 2026-10-15T18:03:09.570Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).