@inproceedings{moradi-etal-2026-flowhn,
    title = "{F}low{HN}: Adaptive Token Routing for Efficient Parallel Hybrid Networks",
    author = "Moradi, Mohammad Mahdi  and
      Ahmed, Walid  and
      Wen, Shuangyue  and
      Mudur, Sudhir  and
      Zhang, Weiwei  and
      Liu, Yang",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-industry.83/",
    pages = "1170--1181",
    ISBN = "979-8-89176-394-4",
    abstract = "Production LLMs must balance modeling quality with predictable latency, stable accelerator utilization, and cost-efficient scaling{---}constraints that remain difficult for existing architectures. Transformers provide strong reasoning but incur quadratic complexity, while state-space models (SSMs) scale efficiently yet lack fine-grained interactions; prior hybrids either introduce sequential bottlenecks or rely on learned routing that complicates deployment. We present FlowHN, a deployment-oriented parallel hybrid architecture that enables deterministic conditional computation via FLOP-aware token circulation across attention and SSM branches. Instead of dynamic expert routing, FlowHN performs hardware-aligned token scheduling that balances workloads, reduces synchronization stalls, and preserves full parameter utilization. Across 135M{--}1B models, FlowHN achieves up to 4{\texttimes} higher throughput and 15{\%} higher MFU than strong Transformer, SSM, and hybrid baselines while maintaining competitive accuracy on reasoning, coding, and long-context tasks up to 32K tokens. FlowHN is designed to integrate directly into existing Hybrid pipelines without changes to optimizers, training stacks, or inference serving infrastructure, making it practical for real-world deployment."
}