Metraipolis › archive › dc_37ee1ecee751

EMMI: Edge Multi-Modal Intelligence for Communication-Efficient MLLM Inference via Fused Representation Compression — arXiv:2609.11058

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.11058
License (as archived): CC0-1.0
Archived: 2026-10-16T05:44:52.860Z
SHA-256 of the archived text: 4f1c285d5aa0aa159b34553cd5714f2d62b407833b00468766d654a24a987e77
Stable URL of this page: https://metraipolis.com/documento/dc_37ee1ecee751

How to cite

EMMI: Edge Multi-Modal Intelligence for Communication-Efficient MLLM Inference via Fused Representation Compression — arXiv:2609.11058 — arXiv (en), https://arxiv.org/abs/2609.11058 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_37ee1ecee751 (Metraipolis archive dc_37ee1ecee751, sha256 4f1c285d5aa0aa159b34553cd5714f2d62b407833b00468766d654a24a987e77)

BibTeX

@misc{dc37ee1ecee751,
  title = {EMMI: Edge Multi-Modal Intelligence for Communication-Efficient MLLM Inference via Fused Representation Compression — arXiv:2609.11058},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11058},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_37ee1ecee751; sha256 4f1c285d5aa0aa159b34553cd5714f2d62b407833b00468766d654a24a987e77},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11058. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in multimodal large language mod- els (MLLMs) have opened new opportunities for edge intelligence by enabling reasoning across heterogeneous sensor modalities, such as vision, text, and telemetry data. However, deploying these capabilities on resource-constrained edge platforms remains challenging due to the substantial computational, memory, and communication demands of modern MLLMs. Rather than transmitting raw sensor observations or partitioning neural networks at intermediate layers, Edge Multi-Modal Intelligence (EMMI) communicates a compact representation between edge devices and server resources, enabling communication-efficient edge MLLM inference. To achieve this, EMMI performs modality-specific encoding, cross-modal representation fusion, and learned compression at the edge, transmitting only a compact latent representation to server-side resources for high-capacity MLLM reasoning. This representation-centric design reduces communication overhead, preserves local data privacy, and provides a fixed-size interface between heterogeneous edge devices and server-side MLLMs. Evaluation on a representative multimodal benchmark demonstrates that EMMI can reduce the communication payload by 32x while maintaining comparable downstream accuracy, resulting in up to a 3.4x reduction in estimated end-to-end inference latency under bandwidth-constrained edge conditions.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-11 in cs.DC).
Categorie arXiv: Machine Learning (cs.LG) ; Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2609.11058 — 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 2026-10-16T05:26:44.603Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).