Imagen de Portada

From Uniform to Adaptive: General Skip-Block Mechanisms for Efficient PDE Neural Operators

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Lei, Yu, Zhongyi, Wang, Hong, Dong, Huanshuo, Xin, Haiyang, Zhao, Hongwei, Li, Bin
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Accelerating IC Thermal Simulation Data Generation via Block Krylov and Operator Action
por: Wang, Hong, et al.
Publicado: (2025)

DSO: Dual-Scale Neural Operators for Stable Long-term Fluid Dynamics Forecasting
por: Dong, Huanshuo, et al.
Publicado: (2026)

STNet: Spectral Transformation Network for Solving Operator Eigenvalue Problem
por: Wang, Hong, et al.
Publicado: (2025)

SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models
por: Tian, Jiayi, et al.
Publicado: (2025)

AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference
por: He, Zhuomin, et al.
Publicado: (2025)

PDEAgent-Bench: A Multi-Metric, Multi-Library Benchmark for PDE Solver Generation
por: Hang, Zhen, et al.
Publicado: (2026)

SkipCat: Rank-Maximized Low-Rank Compression of Large Language Models via Shared Projection and Block Skipping
por: Lu, Yu-Chen, et al.
Publicado: (2025)

Mixture-of-Experts Operator Transformer for Large-Scale PDE Pre-Training
por: Wang, Hong, et al.
Publicado: (2025)

Structure-Aware Epistemic Uncertainty Quantification for Neural Operator PDE Surrogates
por: Song, Haoze, et al.
Publicado: (2026)

Accelerating PDE Data Generation via Differential Operator Action in Solution Space
por: Dong, Huanshuo, et al.
Publicado: (2024)

From Basis to Basis: Gaussian Particle Representation for Interpretable PDE Operators
por: Li, Zhihao, et al.
Publicado: (2026)

CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control
por: Liu, Huanshuo, et al.
Publicado: (2024)

Hierarchical Skip Decoding for Efficient Autoregressive Text Generation
por: Zhu, Yunqi, et al.
Publicado: (2024)

CATO: Charted Attention for Neural PDE Operators
por: Cheng, Chun-Wun, et al.
Publicado: (2026)

GEPS: Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning
por: Koupaï, Armand Kassaï, et al.
Publicado: (2024)

Adaptive Neural-Operator Backstepping Control of a Benchmark Hyperbolic PDE
por: Lamarque, Maxence, et al.
Publicado: (2024)

TimeGMM: Single-Pass Probabilistic Forecasting via Adaptive Gaussian Mixture Models with Reversible Normalization
por: Liu, Lei, et al.
Publicado: (2026)

Multi-Plasticity Synergy with Adaptive Mechanism Assignment for Training Spiking Neural Networks
por: Liu, Yuzhe, et al.
Publicado: (2025)

Memory-Efficient Fine-Tuning Diffusion Transformers via Dynamic Patch Sampling and Block Skipping
por: Park, Sunghyun, et al.
Publicado: (2026)

Employing Deep Neural Operators for PDE control by decoupling training and optimization
por: Lundqvist, Oliver G. S., et al.
Publicado: (2025)

SkipSNN: Efficiently Classifying Spike Trains with Event-attention
por: Yin, Hang, et al.
Publicado: (2024)

NESTOR: A Nested MOE-based Neural Operator for Large-Scale PDE Pre-Training
por: Sun, Dengdi, et al.
Publicado: (2026)

Operator Learning with Domain Decomposition for Geometry Generalization in PDE Solving
por: Huang, Jianing, et al.
Publicado: (2025)

Adaptive GoGI-Skip: Coupling Goal-Gradient Importance with Dynamic Uncertainty for Efficient Reasoning
por: Zhuang, Ren
Publicado: (2025)

BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference
por: Lee, Changwoo, et al.
Publicado: (2024)

On the Adversarial Transferability of Generalized "Skip Connections"
por: Wang, Yisen, et al.
Publicado: (2024)

Can We Formally Verify Neural PDE Surrogates? SMT Compilation of Small Fourier Neural Operators
por: Baheri, Ali, et al.
Publicado: (2026)

Efficient ANN-Guided Distillation: Aligning Rate-based Features of Spiking Neural Networks through Hybrid Block-wise Replacement
por: Yang, Shu, et al.
Publicado: (2025)

Gauge-Equivariant Intrinsic Neural Operators for Geometry-Consistent Learning of Elliptic PDE Maps
por: Cheng, Pengcheng
Publicado: (2026)

SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
por: Chen, Junsong, et al.
Publicado: (2025)

Generative Latent Neural PDE Solver using Flow Matching
por: Li, Zijie, et al.
Publicado: (2025)

Synergizing Kolmogorov-Arnold Networks with Dynamic Adaptive Weighting for High-Frequency and Multi-Scale PDE Solutions
por: Chen, Guokan, et al.
Publicado: (2025)

NeuralMatrix: Compute the Entire Neural Networks with Linear Matrix Operations for Efficient Inference
por: Sun, Ruiqi, et al.
Publicado: (2023)

Climate Downscaling: A Deep-Learning Based Super-resolution Model of Precipitation Data with Attention Block and Skip Connections
por: Chiang, Chia-Hao, et al.
Publicado: (2024)

Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems
por: Hao, Zhezheng, et al.
Publicado: (2026)

Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
por: Wang, Hong, et al.
Publicado: (2024)

SkipSR: Faster Super Resolution with Token Skipping
por: Choudhury, Rohan, et al.
Publicado: (2025)

Prefix-Adaptive Block Diffusion for Efficient Document Recognition
por: Chai, Mingxu, et al.
Publicado: (2026)

Phys-Diff: A Physics-Inspired Latent Diffusion Model for Tropical Cyclone Forecasting
por: Liu, Lei, et al.
Publicado: (2026)

SCNO: Spiking Compositional Neural Operator -- Towards a Neuromorphic Foundation Model for Nuclear PDE Solving
por: Roy, Samrendra, et al.
Publicado: (2026)