Metraipolis › archive › dc_e60201e462a3

Geometric Cross-Modal Token Selection for Latency-Constrained Multimodal Token Communication — arXiv:2608.03141

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03141
License (as archived)
CC0-1.0
Archived
2026-10-31T13:27:47.916Z
SHA-256 of the archived text
d6c2028d504c6e3e09d6e9bdb06661ba9d4e915d642f397edb8eabbe64abc7a0
Stable URL of this page
https://metraipolis.com/documento/dc_e60201e462a3

How to cite

Geometric Cross-Modal Token Selection for Latency-Constrained Multimodal Token Communication — arXiv:2608.03141 — arXiv (en), https://arxiv.org/abs/2608.03141 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e60201e462a3 (Metraipolis archive dc_e60201e462a3, sha256 d6c2028d504c6e3e09d6e9bdb06661ba9d4e915d642f397edb8eabbe64abc7a0)
BibTeX
@misc{dce60201e462a3,
  title = {Geometric Cross-Modal Token Selection for Latency-Constrained Multimodal Token Communication — arXiv:2608.03141},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03141},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e60201e462a3; sha256 d6c2028d504c6e3e09d6e9bdb06661ba9d4e915d642f397edb8eabbe64abc7a0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03141. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper proposes a geometry-based joint cross-modal token selection framework for latency-constrained multimodal token communications. To capture cross-modal token dependencies, we leverage the cross-attention mechanism to project modality-specific tokens into a shared query-key space, where the modality with the fewest tokens serves as the anchor modality and the others as non-anchor modalities. Inspired by germ-grain models, we define an angular-distance metric and construct semantic grain regions around anchor queries. Based on this geometric representation, we identify cross-modal evidence shared across multiple anchor queries in this space and develop an intersection-based token selection (IBS) strategy that prioritizes non-anchor tokens whose key are covered by multiple grain regions. We further develop an erasure-aware extension, termed robust-IBS (R-IBS), for token-wise erasure channels using an expected angular-distance formulation. In both IBS and R-IBS, the grain regions are optimized for individual queries under a latency constraint, using block coordinate descent and a low-complexity greedy algorithm. Simulations corroborate the effectiveness of IBS and R-IBS under latency-constrained and token-wise erasure channels, achieving up to 31.6% and 29.2% task accuracy gains on visual question answering (VQA) and audio-visual question answering (AVQA) tasks, respectively, over existing token selection baselines.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in eess.SP).
Categorie arXiv: Signal Processing (eess.SP).
Pagina del lavoro: https://arxiv.org/abs/2608.03141 — 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 2026-10-31T13:15:13.903Z dalla pagina https://arxiv.org/catchup/eess.SP/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).