# Physics in Next-token Prediction

arXiv: https://arxiv.org/abs/2411.00660 · HTML: https://mlsanity.com/paper/2411.00660/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 6 references that are in the map.
- First posted on arXiv 1 Nov 2024.

## Builds on (most cited first, 1 of 1)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)

## Built on by (most cited first, 1 of 1)

- [Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective](https://mlsanity.com/paper/2412.14135/) (2024)

## Abstract (arXiv)

We discovered the underlying physics in Next-token Prediction (NTP). We identified the law of information conservation within NTP and proposed the First Law of Information Capacity (IC-1), demonstrating that the essence of intelligence emergence in auto-regressive models is fundamentally a process of information transfer. We also introduced Landauer's Principle into NTP, formulating the Second Law of Information Capacity (IC-2), which establishes the relationship between auto-regressive model training and energy consumption. Additionally, we presented several corollaries, which hold practical significance for production practices. Finally, we demonstrate the consistency between the Law of Information Capacity and the Scaling Law for Neural Language Models, the Knowledge Capacity Scaling Laws, and the Scaling Laws for Precision.