Metraipolis › archive › dc_c9eb89e0141b

Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMs — arXiv:2609.31193

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31193
License (as archived)
CC0-1.0
Archived
2026-10-08T03:12:43.988Z
SHA-256 of the archived text
b729374b90ff970828ded76bfc1242429e5a69fefdd15c34e9cee0a017803d96
Stable URL of this page
https://metraipolis.com/documento/dc_c9eb89e0141b

How to cite

Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMs — arXiv:2609.31193 — arXiv (en), https://arxiv.org/abs/2609.31193 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c9eb89e0141b (Metraipolis archive dc_c9eb89e0141b, sha256 b729374b90ff970828ded76bfc1242429e5a69fefdd15c34e9cee0a017803d96)
BibTeX
@misc{dcc9eb89e0141b,
  title = {Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMs — arXiv:2609.31193},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31193},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c9eb89e0141b; sha256 b729374b90ff970828ded76bfc1242429e5a69fefdd15c34e9cee0a017803d96},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31193. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Current Audio-Visual LLMs (AVLLMs) struggle with reasoning over videos featuring multi-speaker dialogues. In such videos, resolving "who says what" is crucial, which necessitates trimodal (text-audio-visual) binding. Motivated by these challenges, we systematically investigate how this trimodal binding is achieved in AVLLMs. Specifically, we identify emergent symbolic trimodal binding mechanisms in AVLLMs that utilize modality-specific symbolic variables. By encoding auditory and visual components into symbolic variables-capturing temporal utterance sequences and spatial entity coordinates, respectively-the model establishes cross-modal linking within this abstract space. Crucially, we reveal that when trimodal binding fails, the breakdown predominantly stems from misaligned audio-visual connections. To overcome this bottleneck, we introduce an audio-visual prompting method utilizing an off-the-shelf Active Speaker Detection (ASD) model. By simply overlaying visual bounding boxes on active speakers, this training-free approach yields immediate performance gains across four conversation-centric benchmarks. Moreover, lightweight fine-tuning of fewer than 300 steps on these ASD-prompted-videos extends these gains to three general AV benchmarks, suggesting the generalizability of our method.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Sound (cs.SD); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2609.31193 — 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 2026-10-08T02:50:19.086Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).