Metraipolis › archive › dc_76c938ccc3ef

Omni-Streaming Thinking — arXiv:2609.15128

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.15128
License (as archived)
CC0-1.0
Archived
2026-10-16T00:11:21.157Z
SHA-256 of the archived text
fbc504dd8f78bf04e8f3ab54f2a0052fe5c1d2a33d84c8e9396785254e676856
Stable URL of this page
https://metraipolis.com/documento/dc_76c938ccc3ef

How to cite

Omni-Streaming Thinking — arXiv:2609.15128 — arXiv (en), https://arxiv.org/abs/2609.15128 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_76c938ccc3ef (Metraipolis archive dc_76c938ccc3ef, sha256 fbc504dd8f78bf04e8f3ab54f2a0052fe5c1d2a33d84c8e9396785254e676856)
BibTeX
@misc{dc76c938ccc3ef,
  title = {Omni-Streaming Thinking — arXiv:2609.15128},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15128},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_76c938ccc3ef; sha256 fbc504dd8f78bf04e8f3ab54f2a0052fe5c1d2a33d84c8e9396785254e676856},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15128. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Streaming omni-modal models must decide what and when to answer from the video chunks and synchronized audio observed so far. Visual cues often support an interpretation before an utterance or sound event is complete. If that interpretation enters memory as a fact, later reasoning can keep relaying it even after audio contradicts it. We call this failure premature cross-modal commitment. We propose Omni-Streaming Thinking (OST), which generates structured outputs that include evidence observed so far, forecasts of future evidence, and claims based on this evidence. Each claim is initially marked as pending and linked to a future verification interval. Audio and visual evidence are stored separately, and OST checks a claim against the evidence from the specified modality at the end of the verification interval. When contradictory evidence is detected, a refutation process reduces the influence of the claim and its dependent states, and then guides a state update using the new evidence. An answer gate decides whether the answer-critical claims meet the conditions for giving a response. Using a frozen Qwen3-Omni-30B-A3B-Instruct backbone with lightweight adaptation, OST outperforms the strongest open baselines on five streaming and audio-visual benchmarks by more than 10% relative on average. We also introduce OST-DiagBench, which holds video fixed and edits audio to test agreement, absence, contradiction, coexistence, and subtitle-speech conflict. OST reaches d-prime = 2.95, compared with at most 1.38 for open baselines, while reducing vision-induced auditory hallucinations.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.15128 — 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 2026-10-15T23:54:14.739Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).