Metraipolis › archive › dc_9dcab784e734

TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming — arXiv:2608.20958

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20958
License (as archived)
CC0-1.0
Archived
2026-10-18T10:56:31.060Z
SHA-256 of the archived text
aacc4a801c1ed6a70f501247486d5ffae8b9047408d2b6c70df51248f4b1c2a4
Stable URL of this page
https://metraipolis.com/documento/dc_9dcab784e734

How to cite

TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming — arXiv:2608.20958 — arXiv (en), https://arxiv.org/abs/2608.20958 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9dcab784e734 (Metraipolis archive dc_9dcab784e734, sha256 aacc4a801c1ed6a70f501247486d5ffae8b9047408d2b6c70df51248f4b1c2a4)
BibTeX
@misc{dc9dcab784e734,
  title = {TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming — arXiv:2608.20958},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20958},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9dcab784e734; sha256 aacc4a801c1ed6a70f501247486d5ffae8b9047408d2b6c70df51248f4b1c2a4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20958. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

E-commerce live streaming requires omni-modal understanding of noisy, temporally extended streams, where product facts are distributed across speech, video frames, product images, overlaid text, and user queries. We present TLive-Omni, an omni-modal understanding model tailored to live-commerce scenarios. It maps image, video, audio, and text inputs into a unified representation space. For long-form live streaming analysis, we introduce Per-vGrid, a timestamped token organization that groups each video grid with its temporally corresponding audio within explicit boundary tokens to facilitate temporal alignment. We design a three-stage supervised training recipe that progressively develops live-commerce understanding, from omni-modal perception to instruction-following responses. We then propose Faithful-RFT, a reinforcement fine-tuning stage that further improves answer faithfulness and expression quality while meeting real-time demands, scoring final responses directly with task-verifiable feedback rather than optimizing for reasoning-style exploration during rollout. Moreover, TLive-Omni is supported by a scenario-oriented atomic capability taxonomy and a compact data production engine that converts live-commerce audio, image, and video streams into training signals for speech recognition, speaker analysis, product visual grounding, text recognition, temporal grounding, video dense caption, and omni-modal QA, etc. For scalable training, a synchronized length-grouped sampler reduces padding while preserving comparable workloads across workers, while a lightweight dynamic sampling strategy regenerates rollout groups with near-zero reward variance to maintain meaningful relative advantages for GRPO. Experiments on e-commerce live streaming benchmarks demonstrate strong performance across live-commerce domain tasks, together with excellent generalization on general benchmarks.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CV).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.20958 — 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 2026-10-18T10:48:13.622Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).