English
Related papers

Related papers: Physics in Next-token Prediction

200 papers

Reasoning over long sequences of observations and actions is essential for many robotic tasks. Yet, learning effective long-context policies from demonstrations remains challenging. As context length increases, training becomes increasingly…

Robotics · Computer Science 2025-05-21 Marcel Torne , Andy Tang , Yuejiang Liu , Chelsea Finn

Landauer's principle introduces a symmetry between computational and physical processes: erasure of information, a logically irreversible operation, must be underlain by an irreversible transformation dissipating energy. Monitoring micro-…

We systematically investigate multi-token prediction (MTP) capabilities within LLMs pre-trained for next-token prediction (NTP). We first show that such models inherently possess MTP capabilities via numerical marginalization over…

Computation and Language · Computer Science 2025-02-14 Somesh Mehra , Javier Alonso Garcia , Lukas Mauch

Form a pure mathematical point of view, common functional forms representing different physical phenomena can be defined. For example, rates of chemical reactions, diffusion and heat transfer are all governed by exponential-type…

Machine Learning · Computer Science 2019-10-01 Navid Zobeiry , Keith D. Humfeld

Can physical concepts and laws emerge in a neural network as it learns to predict the observation data of physical systems? As a benchmark and a proof-of-principle study of this possibility, here we show an introspective learning…

Disordered Systems and Neural Networks · Physics 2019-12-02 Ce Wang , Hui Zhai , Yi-Zhuang You

Thermodynamics, and in particular its first law, is of fundamental importance to Science, and therefore of great general interest to all physicists. The first law, although undoubtedly true, and believed by everyone to be true because of…

Statistical Mechanics · Physics 2007-05-23 S. Martinez , A. Plastino , B. H. Soffer

We develop a formulation of particle mechanics in which the functional relation between force and kinetic energy is derived directly from local conservation mechanical energy $E$, rather than postulated through Newton's second law or a…

Classical Physics · Physics 2026-02-10 Thomas Oikonomou

Extending the quantum formulation of [Phys. Rev. X 3, 041003 (2013)] to a more general setting for studying the thermodynamics of information processing including initial correlations, we generalize the second law of thermodynamics to…

Quantum Physics · Physics 2025-11-13 Shou-I Tang , Emery Doucet , Akram Touil , Sebastian Deffner , Akira Sone

Future sequence represents the outcome after executing the action into the environment (i.e. the trajectory onwards). When driven by the information-theoretic concept of mutual information, it seeks maximally informative consequences.…

Machine Learning · Computer Science 2023-11-15 Jianfei Ma

Recently, machine learning techniques, particularly deep learning, have demonstrated superior performance over traditional time series forecasting methods across various applications, including both single-variable and multi-variable…

Machine Learning · Computer Science 2025-10-02 Huaiyuan Rao , Yichen Zhao , Qiang Lai

The next-token prediction (NTP) objective trains language models to predict a single token at each step, even though many continuations can express the same meaning. For example, in the sentence ``this sticker can be placed here'',…

Computation and Language · Computer Science 2026-05-26 Christine Zhang , Dan Jurafsky , Chen Shani

Thermodynamics connects our knowledge of the world to our capability to manipulate and thus to control it. This crucial role of control is exemplified by the third law of thermodynamics, Nernst's unattainability principle, which states that…

Neural models combining representation learning and reasoning in an end-to-end trainable manner are receiving increasing interest. However, their use is severely limited by their computational complexity, which renders them unusable on real…

Artificial Intelligence · Computer Science 2018-07-24 Pasquale Minervini , Matko Bosnjak , Tim Rocktäschel , Sebastian Riedel

Modelling student knowledge is a key challenge when leveraging AI in education, with major implications for personalised learning. The Knowledge Tracing (KT) task aims to predict how students will respond to educational questions in…

Computation and Language · Computer Science 2026-01-27 Max Norris , Kobi Gal , Sahan Bulathwela

A kinetic approach to the notion of information is proposed, based on Liouville kinetic theory. The general kinetic equation for the evolution of the N-particle information $\mathcal{I}_N$ in a Hamiltonian system of large particle number…

Statistical Mechanics · Physics 2015-03-11 R. A. Treumann , W. Baumjohann

Laplace's first law of errors, which states that the frequency of an error can be represented as an exponential function of the error magnitude, was overlooked for many decades but was recently shown to describe the statistical behavior of…

Statistical Mechanics · Physics 2025-01-13 Lucianno Defaveri , Eli Barkai

While frameworks based on physical grounds (like the Drift-Diffusion Model) have been exhaustively used in psychology and neuroscience to describe perceptual decision-making in humans, analogous approaches for more complex situations like…

Physics and Society · Physics 2022-12-19 Javier Cristín , Vicenç Méndez , Daniel Campos

We study diffusion of information packets on several classes of structured networks. Packets diffuse from a randomly chosen node to a specified destination in the network. As local transport rules we consider random diffusion and an…

Statistical Mechanics · Physics 2015-06-24 Bosiljka Tadic , Stefan Thurner

Our main models of computation (the Turing Machine and the RAM) make fundamental assumptions about which primitive operations are realizable. The consensus is that these include logical operations like conjunction, disjunction and negation,…

Programming Languages · Computer Science 2018-12-12 Jacques Carette , Roshan P. James , Amr Sabry

Next-token prediction is conventionally done using decoder-only Transformers with causal attention, as this approach allows for efficient reuse of keys and values. What if we were not compute-limited, should we still use decoder-only…

Machine Learning · Computer Science 2025-02-05 Ethan Ewer , Daewon Chae , Thomas Zeng , Jinkyu Kim , Kangwook Lee
‹ Prev 1 8 9 10 Next ›