🧑‍🔬 Ziming Liu

🏛️ Affiliations

🎓Massachusetts Institute of TechnologyCambridge · United States2021–2026 · 33 papers🔬The NSF AI Institute for Artificial Intelligence and Fundamental InteractionsCambridge · United States2021–2026 · 18 papers🎓Tsinghua UniversityBeijing · China2026 · 6 papers🔬Shanghai Qi Zhi InstituteShanghai · China2026 · 4 papers🎓Peking UniversityBeijing · China2019–2021 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. AI Poincaré: Machine Learning Conservation Laws from Trajectories (2020 · 130 citations)
   The paper asks whether conservation laws can be found purely from observed trajectories, without knowing the equations of motion.
2. Towards Understanding Grokking: An Effective Theory of Representation Learning (2022 · 65 citations)
   Grokking is the behavior where a neural network fits its training data early but only begins to generalize much later.
3. The Quantization Model of Neural Scaling (2023 · 30 citations)
   The paper tackles a puzzle about scaling. Average loss falls smoothly as a power law when models and datasets grow, yet specific abilities often seem to switch on abruptly. To reconcile the two, the authors propose the Quantization Hypothesis. It holds that prediction tasks rely on a countable set of discrete skills…
4. Omnigrok: Grokking Beyond Algorithmic Data (2022 · 29 citations)
   Grokking is when a network fits its training data early but only begins to generalize much later. It had been documented mainly on algorithmic tasks, and its cause was unclear. Liu, Michaud and Tegmark study it through loss-landscape geometry. They use a "reduced" loss, obtained by optimizing over weight directions…
5. Do Two AI Scientists Agree? (2025)
   The paper asks whether independently trained AI models given the same physics data arrive at the same theory or at different ones.

🤝 Co-authors here

3 co-authors with a page, the most papers together first.

• Max Tegmark ×5
• Eric J. Michaud ×3
• Niklas Nolte

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2022
• Physical Review Letters: Physical Review Letters 2020

🔗 Cited by

Papers of our library cite their works 80 times (of the 149,439 papers whose bibliographies we read); 26 citing papers with a page here →.

Updated 3 November 2026

This page in Markdown → https://md.research.elamur.ai/free/en/authors/ziming-liu/