Transformers operate as horizontal token-by-token scanners; at each generation step, attending to an ever-growing sequence of token-level states. This access pattern increases prefill latency and makes long-context decoding more memory-bound, as KV-cache reads and writes dominate inference time over arithmetic operations. We propose Parallel Hierarchical Operation for TOp-down Networks (PHOTON), a hierarchical autoregressive model that replaces horizontal scanning with vertical, multi-resolution context scanning. PHOTON maintains a hierarchy of latent streams: a bottom-up encoder compresses tokens into low-rate contextual states, while lightweight top-down decoders reconstruct fine-grained token representations in parallel. We further introduce recursive generation that updates only the coarsest latent stream and eliminates bottom-up re-encoding. Experimental results show that PHOTON is superior to competitive Transformer-based language models regarding the throughput-quality trade-off, providing advantages in long-context and multi-query tasks. In particular, this reduces decode-time KV-cache traffic, yielding up to 103× higher throughput per unit memory.
@article{arxiv.2512.20687,
title = {PHOTON: Hierarchical Autoregressive Modeling for Lightspeed and Memory-Efficient Language Generation},
author = {Yuma Ichikawa and Naoya Takagi and Takumi Nakagawa and Yuzi Kanazawa and Akira Sakai},
journal= {arXiv preprint arXiv:2512.20687},
year = {2026}
}