[2507.12549] The Serial Scaling Hypothesis

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[2507.12549] The Serial Scaling Hypothesis Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Machine Learning arXiv:2507.12549 (cs) [Submitted on 16 Jul 2025 ( v1 ), last revised 28 Apr 2026 (this version, v4)] Title: The Serial Scaling Hypothesis Authors: Yuxi Liu , Konpat Preechakul , Kananart Kuwaranancharoen , Yutong Bai View a PDF of the paper titled The Serial Scaling Hypothesis, by Yuxi Liu and 3 other authors View PDF HTML (experimental) Abstract: While machine learning has a

related reading

• [2507.12549] The Serial Scaling Hypothesisarxiv.org
• How To Scale Your Modeljax-ml.github.io
• The Scaling Hypothesis · Gwern.netgwern.net
• (Some of) The Models, They Just Don't Want to Learn | Tildeblog.tilderesearch.com
• Scaling Laws, Carefully | Lil'Loglilianweng.github.io
• On neural scaling and the quanta hypothesisericjmichaud.com
• Scaling is subtler than it seemsberen.io
• machine learning imindslice.substack.com
• My picture of the present in AI — LessWronglesswrong.com
• IsoCompute Playbook: Optimally Scaling Sampling Compute for RL Training of LLMscompute-optimal-rl-llm-scaling.github.io
• Will scaling work? - by Dwarkesh Patel - Dwarkesh Podcastdwarkesh.com
• Ilya Sutskever — We're moving from the age of scaling to the age of researchdwarkesh.com