Imagen de Portada

On the Invariance and Generality of Neural Scaling Laws

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Han, Xing, Liu, Ziyin, Saria, Suchi, Liang, Paul Pu
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Massively Multimodal Foundation Models: A Framework for Capturing Interactions with Specialized Mixture-of-Experts
por: Han, Xing, et al.
Publicado: (2025)

WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales
por: Prinster, Drew, et al.
Publicado: (2025)

FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning
por: Han, Xing, et al.
Publicado: (2026)

FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion
por: Han, Xing, et al.
Publicado: (2024)

On Expert Estimation in Hierarchical Mixture of Experts: Beyond Softmax Gating Functions
por: Nguyen, Huy, et al.
Publicado: (2024)

Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them)
por: Prinster, Drew, et al.
Publicado: (2024)

Open-Set Domain Adaptation Under Background Distribution Shift: Challenges and A Provably Efficient Solution
por: Chaudhari, Shravan, et al.
Publicado: (2025)

MILM: Large Language Models for Multimodal Irregular Time Series with Informative Sampling
por: Chung, Hsing-Huan, et al.
Publicado: (2026)

Data Augmentations for Improved (Large) Language Model Generalization
por: Feder, Amir, et al.
Publicado: (2023)

Between Linear and Sinusoidal: Rethinking the Time Encoder in Dynamic Graph Learning
por: Chung, Hsing-Huan, et al.
Publicado: (2025)

Improving Coverage in Combined Prediction Sets with Weighted p-values
por: Wong, Gina, et al.
Publicado: (2025)

Topological Invariance and Breakdown in Learning
por: Yang, Yongyi, et al.
Publicado: (2025)

Understanding the Emergence of Multimodal Representation Alignment
por: Tjandrasuwita, Megan, et al.
Publicado: (2025)

Conformal Policy Control
por: Prinster, Drew, et al.
Publicado: (2026)

Symmetry Induces Structure and Constraint of Learning
por: Ziyin, Liu
Publicado: (2023)

Towards Neural Scaling Laws for Time Series Foundation Models
por: Yao, Qingren, et al.
Publicado: (2024)

Compositional Generalization via Forced Rendering of Disentangled Latents
por: Liang, Qiyao, et al.
Publicado: (2025)

Neural Neural Scaling Laws
por: Hu, Michael Y., et al.
Publicado: (2026)

Towards Neural Scaling Laws on Graphs
por: Liu, Jingzhe, et al.
Publicado: (2024)

Towards Multi-Fidelity Scaling Laws of Neural Surrogates in CFD
por: Setinek, Paul, et al.
Publicado: (2025)

An Equivariance Toolbox for Learning Dynamics
por: Yang, Yongyi, et al.
Publicado: (2025)

ScaleNet: Scale Invariance Learning in Directed Graphs
por: Jiang, Qin, et al.
Publicado: (2024)

ReBaNO: Reduced Basis Neural Operator Mitigating Generalization Gaps and Achieving Discretization Invariance
por: Zheng, Haolan, et al.
Publicado: (2025)

Unified Neural Network Scaling Laws and Scale-time Equivalence
por: Boopathy, Akhilan, et al.
Publicado: (2024)

Configuration-to-Performance Scaling Law with Neural Ansatz
por: Zhang, Huaqing, et al.
Publicado: (2026)

Breaking Neural Network Scaling Laws with Modularity
por: Boopathy, Akhilan, et al.
Publicado: (2024)

Progressive Compositionality in Text-to-Image Generative Models
por: Han, Evans Xu, et al.
Publicado: (2024)

On the Optimizer Dependence of Neural Scaling Laws
por: Ramani, Vansh, et al.
Publicado: (2026)

Accurate and Scalable Graph Neural Networks via Message Invariance
por: Shi, Zhihao, et al.
Publicado: (2025)

Formation of Representations in Neural Networks
por: Ziyin, Liu, et al.
Publicado: (2024)

MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping
por: Shan, Xiaojun, et al.
Publicado: (2025)

Three Mechanisms of Feature Learning in a Linear Network
por: Xu, Yizhou, et al.
Publicado: (2024)

Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra
por: Worschech, Roman, et al.
Publicado: (2024)

Out-of-Distribution Generalized Dynamic Graph Neural Network with Disentangled Intervention and Invariance Promotion
por: Zhang, Zeyang, et al.
Publicado: (2023)

Explaining Neural Scaling Laws
por: Bahri, Yasaman, et al.
Publicado: (2021)

Model Metamers Reveal Invariances in Graph Neural Networks
por: Xu, Wei, et al.
Publicado: (2025)

Towards Invariance to Node Identifiers in Graph Neural Networks
por: Bechler-Speicher, Maya, et al.
Publicado: (2025)

Neural Scaling Laws for Deep Regression
por: Cadez, Tilen, et al.
Publicado: (2025)

Scaling Laws for Neural Material Models
por: Trikha, Akshay, et al.
Publicado: (2025)

AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws
por: Neumann, Oren, et al.
Publicado: (2024)