Metraipolis › archive › dc_2f1fdb9dda29

Beyond Global Routing Aggregation: Phase-Aware Expert Merging for MoE Vision-Language Models — arXiv:2608.04454

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04454
License (as archived)
CC0-1.0
Archived
2026-10-31T11:35:41.765Z
SHA-256 of the archived text
0a976f9458ada725f5f8b8e5d6cd8604c994d62d00b46367fdbb9b48243d734b
Stable URL of this page
https://metraipolis.com/documento/dc_2f1fdb9dda29

How to cite

Beyond Global Routing Aggregation: Phase-Aware Expert Merging for MoE Vision-Language Models — arXiv:2608.04454 — arXiv (en), https://arxiv.org/abs/2608.04454 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f1fdb9dda29 (Metraipolis archive dc_2f1fdb9dda29, sha256 0a976f9458ada725f5f8b8e5d6cd8604c994d62d00b46367fdbb9b48243d734b)
BibTeX
@misc{dc2f1fdb9dda29,
  title = {Beyond Global Routing Aggregation: Phase-Aware Expert Merging for MoE Vision-Language Models — arXiv:2608.04454},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04454},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f1fdb9dda29; sha256 0a976f9458ada725f5f8b8e5d6cd8604c994d62d00b46367fdbb9b48243d734b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04454. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Mixture-of-experts vision-language models (MoE-VLMs) increase model capacity with sparse expert activation, yet deployment requires storing the full expert pool. Training-free expert merging reduces this burden, and many routing-based methods aggregate routing statistics across all tokens to determine merge compatibility. However, MoE-VLM inference is phase-structured: image-context tokens carry visual content, question tokens specify the query, and answer tokens produce the output, with different counts and routing distributions. Because image-context tokens are far more numerous, global aggregation can overemphasize image-context processing and obscure phase-conditioned expert roles, making experts serving different phases appear interchangeable and degrading model performance. We therefore argue that MoE-VLM expert merging should preserve phase-conditioned expert roles, judging compatibility by how experts serve different phases rather than globally aggregated routing statistics. Based on this view, we propose RoleMerge, a training-free method that constructs each expert's Routing Role Profile (RRP) from phase-normalized routing statistics, capturing its relative phase preference. Guided by expert-phase information loss, RoleMerge merges experts with compatible profiles and their corresponding router entries while preserving answer-decoding expert distinctions. Experiments on three models and multiple benchmarks show that RoleMerge preserves more of the full model's performance than alternative expert-merging methods at matched expert-retention ratios, with relative improvements of up to 9.6 percent in six-task macro-average performance. These results validate phase-conditioned expert roles as a more effective basis than global routing aggregation for MoE-VLM expert merging.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.04454 — 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 2026-10-31T11:24:48.831Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).