{"ID":2844411,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.06441","arxiv_id":"2511.06441","title":"Towards Resource-Efficient Multimodal Intelligence: Learned Routing among Specialized Expert Models","abstract":"As AI moves beyond text, large language models (LLMs) increasingly power vision, audio, and document understanding; however, their high inference costs hinder real-time, scalable deployment. Conversely, smaller open-source models offer cost advantages but struggle with complex or multimodal queries. We introduce a unified, modular framework that intelligently routes each query - textual, multimodal, or complex - to the most fitting expert model, using a learned routing network that balances cost and quality. For vision tasks, we employ a two-stage open-source pipeline optimized for efficiency and reviving efficient classical vision components where they remain SOTA for sub-tasks. On benchmarks such as Massive Multitask Language Understanding (MMLU) and Visual Question Answering (VQA), we match or exceed the performance of always-premium LLM (monolithic systems with one model serving all query types) performance, yet reduce the reliance on costly models by over 67%. With its extensible, multi-agent orchestration, we deliver high-quality, resource-efficient AI at scale.","short_abstract":"As AI moves beyond text, large language models (LLMs) increasingly power vision, audio, and document understanding; however, their high inference costs hinder real-time, scalable deployment. Conversely, smaller open-source models offer cost advantages but struggle with complex or multimodal queries. We introduce a unif...","url_abs":"https://arxiv.org/abs/2511.06441","url_pdf":"https://arxiv.org/pdf/2511.06441v1","authors":"[\"Mayank Saini\",\"Arit Kumar Bishwas\"]","published":"2025-11-09T16:14:56Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}