Image de couverture de livre

LLMs learn governing principles of dynamical systems, revealing an in-context neural scaling law

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Toni J. B., Boullé, Nicolas, Sarfati, Raphaël, Earls, Christopher J.
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Density estimation with LLMs: a geometric investigation of in-context learning trajectories
par: Liu, Toni J. B., et autres
Publié: (2024)

Jacobian Scopes: token-level causal attributions in LLMs
par: Liu, Toni J. B., et autres
Publié: (2026)

Text-Trained LLMs Can Zero-Shot Extrapolate PDE Dynamics, Revealing a Three-Stage In-Context Learning Mechanism
par: Bao, Jiajun, et autres
Publié: (2025)

Lines of Thought in Large Language Models
par: Sarfati, Raphaël, et autres
Publié: (2024)

What's in a prompt? Language models encode literary style in prompt embeddings
par: Sarfati, Raphaël, et autres
Publié: (2025)

Bayesian scaling laws for in-context learning
par: Arora, Aryaman, et autres
Publié: (2024)

A Mathematical Guide to Operator Learning
par: Boullé, Nicolas, et autres
Publié: (2023)

Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods
par: Zekri, Oussama, et autres
Publié: (2025)

Operator learning without the adjoint
par: Boullé, Nicolas, et autres
Publié: (2024)

Enhanced Transformer architecture for in-context learning of dynamical systems
par: Rufolo, Matteo, et autres
Publié: (2024)

Training instability in deep learning follows low-dimensional dynamical principles
par: Zhang, Zhipeng, et autres
Publié: (2026)

Generalized Discrete Diffusion from Snapshots
par: Zekri, Oussama, et autres
Publié: (2026)

Bound by semanticity: universal laws governing the generalization-identification tradeoff
par: Nurisso, Marco, et autres
Publié: (2025)

Automated discovery of symbolic laws governing skill acquisition from naturally occurring data
par: Liu, Sannyuya, et autres
Publié: (2024)

Conditional computation in neural networks: principles and research trends
par: Scardapane, Simone, et autres
Publié: (2024)

In-context learning and Occam's razor
par: Elmoznino, Eric, et autres
Publié: (2024)

Analyzing limits for in-context learning
par: Naim, Omar, et autres
Publié: (2025)

Similarity-based context aware continual learning for spiking neural networks
par: Han, Bing, et autres
Publié: (2024)

On the origin of neural scaling laws: from random graphs to natural language
par: Barkeshli, Maissam, et autres
Publié: (2026)

Diffusion models as probabilistic neural operators for recovering unobserved states of dynamical systems
par: Haitsiukevich, Katsiaryna, et autres
Publié: (2024)

Reproducible scaling laws for contrastive language-image learning
par: Cherti, Mehdi, et autres
Publié: (2022)

Scaling laws for learning with real and surrogate data
par: Jain, Ayush, et autres
Publié: (2024)

Next-token pretraining implies in-context learning
par: Riechers, Paul M., et autres
Publié: (2025)

Does learning the right latent variables necessarily improve in-context learning?
par: Mittal, Sarthak, et autres
Publié: (2024)

Scalable and reliable deep transfer learning for intelligent fault detection via multi-scale neural processes embedded with knowledge
par: Li, Zhongzhi, et autres
Publié: (2024)

Decomposing heterogeneous dynamical systems with graph neural networks
par: Allier, Cédric, et autres
Publié: (2024)

Logic-informed reinforcement learning for cross-domain optimization of large-scale cyber-physical systems
par: Wan, Guangxi, et autres
Publié: (2025)

Large Language Models as Markov Chains
par: Zekri, Oussama, et autres
Publié: (2024)

ICPL: Few-shot In-context Preference Learning via LLMs
par: Yu, Chao, et autres
Publié: (2024)

Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
par: Boppana, Siddharth, et autres
Publié: (2026)

A Decomposition Perspective to Long-context Reasoning for LLMs
par: Xiao, Yanling, et autres
Publié: (2026)

Understanding the dynamics of the frequency bias in neural networks
par: Molina, Juan, et autres
Publié: (2024)

A deep learning and machine learning approach to predict neonatal death in the context of São Paulo
par: Raihan, Mohon, et autres
Publié: (2025)

Scientific machine learning in ecological systems: A study on the predator-prey dynamics
par: Devgupta, Ranabir, et autres
Publié: (2024)

The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations
par: Boix-Adsera, Enric, et autres
Publié: (2025)

TSFM in-context learning for time-series classification of bearing-health status
par: Tokic, Michel, et autres
Publié: (2025)

RAGuard: A Novel Approach for in-context Safe Retrieval Augmented Generation for LLMs
par: Walker, Connor, et autres
Publié: (2025)

Evidence for Limited Metacognition in LLMs
par: Ackerman, Christopher
Publié: (2025)

Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families
par: Polo, Felipe Maia, et autres
Publié: (2024)

Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL
par: Pignatelli, Eduardo, et autres
Publié: (2024)