Imagen de Portada

Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Chen, Hu, Siyu, Tan, Guangming, Jia, Weile
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

MatRIS: Toward Reliable and Efficient Pretrained Machine Learning Interatomic Potentials
por: Zhou, Yuanchang, et al.
Publicado: (2026)

FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs
por: Zhou, Yuanchang, et al.
Publicado: (2024)

Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning
por: Zhao, Lifan, et al.
Publicado: (2025)

Compact Language Models via Pruning and Knowledge Distillation
por: Muralidharan, Saurav, et al.
Publicado: (2024)

Are Foundational Atomistic Models Reliable for Finite-Temperature Molecular Dynamics?
por: Li, Denan, et al.
Publicado: (2025)

WISCA: A Lightweight Model Transition Method to Improve LLM Training via Weight Scaling
por: Li, Jiacheng, et al.
Publicado: (2025)

CUT: Pruning Pre-Trained Multi-Task Models into Compact Models for Edge Devices
por: Zhou, Jingxuan, et al.
Publicado: (2025)

Breaking the Training Barrier of Billion-Parameter Universal Machine Learning Interatomic Potentials
por: Zhou, Yuanchang, et al.
Publicado: (2026)

Information Routing in Atomistic Foundation Models: How Task Alignment and Equivariance Shape Linear Disentanglement
por: Steier, Joshua
Publicado: (2026)

Efficient Prediction of SO(3)-Equivariant Hamiltonian Matrices via SO(2) Local Frames
por: Yu, Haiyang, et al.
Publicado: (2025)

FASP: Fast and Accurate Structured Pruning of Large Language Models
por: Hu, Hanyu, et al.
Publicado: (2025)

SR-PredictAO: Session-based Recommendation with High-Capability Predictor Add-On
por: Wang, Ruida, et al.
Publicado: (2023)

Pruning for Sparse Diffusion Models based on Gradient Flow
por: Wan, Ben, et al.
Publicado: (2025)

Mathematical Foundation of Interpretable Equivariant Surrogate Models
por: Colombini, Jacopo Joy, et al.
Publicado: (2025)

SlimLLM: Accurate Structured Pruning for Large Language Models
por: Guo, Jialong, et al.
Publicado: (2025)

Reconstruct the Pruned Model without Any Retraining
por: Wang, Pingjie, et al.
Publicado: (2024)

Exploring Landscapes for Better Minima along Valleys
por: Zhao, Tong, et al.
Publicado: (2025)

A Materials Foundation Model via Hybrid Invariant-Equivariant Architectures
por: Yan, Keqiang, et al.
Publicado: (2025)

Prune, Update and Trim: Robust Structured Pruning for Large Language Models
por: Mecke, Diego Coello de Portugal, et al.
Publicado: (2026)

MaskPrune: Mask-based LLM Pruning for Layer-wise Uniform Structures
por: Qin, Jiayu, et al.
Publicado: (2025)

PaMM: Periodic Motif Memory for Atomistic Models with an Explicit Local-Structure Interface
por: Dong, Ryan
Publicado: (2026)

Direct Molecular Polarizability Prediction with SO(3) Equivariant Local Frame GNNs
por: Filling, Jean Philip, et al.
Publicado: (2025)

SPAP: Structured Pruning via Alternating Optimization and Penalty Methods
por: Hu, Hanyu, et al.
Publicado: (2025)

EquiJump: Protein Dynamics Simulation via SO(3)-Equivariant Stochastic Interpolants
por: Costa, Allan dos Santos, et al.
Publicado: (2024)

MatterTune: An Integrated, User-Friendly Platform for Fine-Tuning Atomistic Foundation Models to Accelerate Materials Simulation and Discovery
por: Kong, Lingyu, et al.
Publicado: (2025)

Pruning Foundation Models for High Accuracy without Retraining
por: Zhao, Pu, et al.
Publicado: (2024)

BMRS: Bayesian Model Reduction for Structured Pruning
por: Wright, Dustin, et al.
Publicado: (2024)

Quantized SO(3)-Equivariant Graph Neural Networks for Efficient Molecular Property Prediction
por: Zhou, Haoyu, et al.
Publicado: (2026)

SO(3)-Equivariant Neural Networks for Learning from Scalar and Vector Fields on Spheres
por: Ballerin, Francesco, et al.
Publicado: (2025)

Elign: Equivariant Diffusion Model Alignment from Foundational Machine Learning Force Fields
por: Li, Yunyang, et al.
Publicado: (2026)

Equivariant-Aware Structured Pruning for Efficient Edge Deployment: A Comprehensive Framework with Adaptive Fine-Tuning
por: Alnemari, Mohammed
Publicado: (2025)

SO(2)-Equivariant Downwash Models for Close Proximity Flight
por: Smith, H., et al.
Publicado: (2023)

Structure-based Drug Design with Equivariant Diffusion Models
por: Schneuing, Arne, et al.
Publicado: (2022)

ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
por: Liu, Lawrence, et al.
Publicado: (2025)

Quasi-Equivariant Metanetworks
por: Tran, Viet-Hoang, et al.
Publicado: (2026)

Preserving Continuous Symmetry in Discrete Spaces: Geometric-Aware Quantization for SO(3)-Equivariant GNNs
por: Zhou, Haoyu, et al.
Publicado: (2026)

Restoring Pruned Large Language Models via Lost Component Compensation
por: Feng, Zijian, et al.
Publicado: (2025)

Deterministic Differentiable Structured Pruning for Large Language Models
por: Huang, Weiyu, et al.
Publicado: (2026)

Incorporating Arbitrary Matrix Group Equivariance into KANs
por: Hu, Lexiang, et al.
Publicado: (2024)

Compact Matrix Quantum Group Equivariant Neural Networks
por: Pearce-Crump, Edward
Publicado: (2023)