The Serial Scaling Hypothesis
Abstract
While machine learning has advanced through massive parallelization, we identify a critical blind spot: some problems are fundamentally sequential. These "inherently serial" problems—from mathematical reasoning to physical simulations to sequential decision-making—require sequentially dependent computational steps that cannot be efficiently parallelized. We formalize this distinction in complexity theory, and demonstrate that current parallel-centric architectures face fundamental limitations on such tasks. Then, we show for first time that diffusion models despite their sequential nature are incapable of solving inherently serial problems. We argue that recognizing the serial nature of computation holds profound implications on machine learning, model design, and hardware development.
Cite
Text
Liu et al. "The Serial Scaling Hypothesis." International Conference on Learning Representations, 2026.Markdown
[Liu et al. "The Serial Scaling Hypothesis." International Conference on Learning Representations, 2026.](https://mlanthology.org/iclr/2026/liu2026iclr-serial/)BibTeX
@inproceedings{liu2026iclr-serial,
title = {{The Serial Scaling Hypothesis}},
author = {Liu, Yuxi and Preechakul, Konpat and Kuwaranancharoen, Kananart and Bai, Yutong},
booktitle = {International Conference on Learning Representations},
year = {2026},
url = {https://mlanthology.org/iclr/2026/liu2026iclr-serial/}
}