Imagen de Portada

When Do Neural Networks Learn World Models?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Tianren, Chen, Guanyu, Chen, Feng
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Reconciling In-Context and In-Weight Learning via Dual Representation Space Encoding
por: Chen, Guanyu, et al.
Publicado: (2026)

Feature contamination: Neural networks learn uncorrelated features and fail to generalize
por: Zhang, Tianren, et al.
Publicado: (2024)

Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them
por: Chen, Guanyu, et al.
Publicado: (2025)

A method of supervised learning from conflicting data with hidden contexts
por: Zhang, Tianren, et al.
Publicado: (2021)

Graph World Model
por: Feng, Tao, et al.
Publicado: (2025)

Preserving Silent Features for Domain Generalization
por: Zhao, Chujie, et al.
Publicado: (2024)

What to Do When Your Discrete Optimization Is the Size of a Neural Network?
por: Silva, Hugo, et al.
Publicado: (2024)

Do Graph Neural Networks Work for High Entropy Alloys?
por: Zhang, Hengrui, et al.
Publicado: (2024)

When Models Know When They Do Not Know: Calibration, Cascading, and Cleaning
por: Hao, Chenjie, et al.
Publicado: (2026)

Do Neural Networks Lose Plasticity in a Gradually Changing World?
por: Liu, Tianhui, et al.
Publicado: (2026)

Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning
por: Hao, Chenjie, et al.
Publicado: (2025)

DGNN: A Neural PDE Solver Induced by Discontinuous Galerkin Methods
por: Chen, Guanyu, et al.
Publicado: (2025)

When Do Graph Foundation Models Transfer? A Data-Centric Theory
por: Zhu, Jiajun, et al.
Publicado: (2026)

Multimodal machine learning with large language embedding model for polymer property prediction
por: Zhang, Tianren, et al.
Publicado: (2025)

Mixture-of-World Models: Scaling Multi-Task Reinforcement Learning with Modular Latent Dynamics
por: Zhang, Boxuan, et al.
Publicado: (2026)

The Challenger: When Do New Data Sources Justify Switching Machine Learning Models?
por: Digalakis Jr, Vassilis, et al.
Publicado: (2025)

When do World Models Successfully Learn Dynamical Systems?
por: Ross, Edmund, et al.
Publicado: (2025)

Hysteresis-Aware Neural Network Modeling and Whole-Body Reinforcement Learning Control of Soft Robots
por: Chen, Zongyuan, et al.
Publicado: (2025)

TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models
por: Li, Ding, et al.
Publicado: (2024)

Epistemic Deep Learning: Enabling Machine Learning Models to Know When They Do Not Know
por: Manchingal, Shireen Kudukkil
Publicado: (2025)

Parameter Identification for Partial Differential Equation with Jump Discontinuities in Coefficients by Markov Switching Model and Physics-Informed Machine Learning
por: Zhang, Zhikun, et al.
Publicado: (2025)

Rethinking Structure Learning For Graph Neural Networks
por: Zheng, Yilun, et al.
Publicado: (2024)

When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective
por: Mousavi-Hosseini, Alireza, et al.
Publicado: (2025)

When Do Neural Nets Outperform Boosted Trees on Tabular Data?
por: McElfresh, Duncan, et al.
Publicado: (2023)

Graph Neural Networks for Learning Equivariant Representations of Neural Networks
por: Kofinas, Miltiadis, et al.
Publicado: (2024)

When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Models
por: Guo, Zhixiang, et al.
Publicado: (2026)

Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction
por: Ye, Zesheng, et al.
Publicado: (2025)

When Brain Networks Travel: Learning Beyond Site
por: Wang, Yingxu, et al.
Publicado: (2026)

When Graph Neural Networks Meet Dynamic Mode Decomposition
por: Shi, Dai, et al.
Publicado: (2024)

Learning Interactive World Model for Object-Centric Reinforcement Learning
por: Feng, Fan, et al.
Publicado: (2025)

Curriculum Learning of Physics-Informed Neural Networks based on Spatial Correlation
por: Chen, Xujia, et al.
Publicado: (2026)

When Do Graph Neural Networks Help with Node Classification? Investigating the Impact of Homophily Principle on Node Distinguishability
por: Luan, Sitao, et al.
Publicado: (2023)

Do Neural Scaling Laws Exist on Graph Self-Supervised Learning?
por: Ma, Qian, et al.
Publicado: (2024)

Neighborhood Sampling Does Not Learn the Same Graph Neural Network
por: Niu, Zehao, et al.
Publicado: (2025)

Towards Dynamic Graph Neural Networks with Provably High-Order Expressive Power
por: Wang, Zhe, et al.
Publicado: (2024)

Evidential Uncertainty Probes for Graph Neural Networks
por: Yu, Linlin, et al.
Publicado: (2025)

DPGNN: Dual-Perception Graph Neural Network for Representation Learning
por: Zhou, Li, et al.
Publicado: (2021)

A Unified Kernel for Neural Network Learning
por: Zhang, Shao-Qun, et al.
Publicado: (2024)

What Do Latent Action Models Actually Learn?
por: Zhang, Chuheng, et al.
Publicado: (2025)

A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
por: Li, Jintang, et al.
Publicado: (2023)