Cover Image

Beyond Attention: True Adaptive World Models via Spherical Kernel Operator

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Khasia, Vladimer
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

HAS-VQ: Hessian-Adaptive Sparse Vector Quantization for High-Fidelity LLM Compression
by: Khasia, Vladimer
Published: (2026)

The Adaptive Vekua Cascade: A Differentiable Spectral-Analytic Solver for Physics-Informed Representation
by: Khasia, Vladimer
Published: (2025)

Dynamic Subspace Composition: Efficient Adaptation via Contractive Basis Expansion
by: Khasia, Vladimer
Published: (2025)

The Vekua Layer: Exact Physical Priors for Implicit Neural Representations via Generalized Analytic Functions
by: Khasia, Vladimer
Published: (2025)

HoloByte: Continuous Hyperspherical Distillation for Tokenizer-Free Modeling
by: Khasia, Vladimer
Published: (2026)

Hybrid Dual-Path Linear Transformations for Efficient Transformer Architectures
by: Khasia, Vladimer
Published: (2026)

BASIS: Balanced Activation Sketching with Invariant Scalars for "Ghost Backpropagation"
by: Khasia, Vladimer
Published: (2026)

Spectral-Window Hybrid (SWH)
by: Khasia, Vladimer
Published: (2026)

DeepVekua: Geometric-Spectral Representation Learning for Physics-Informed Fields
by: Khasia, Vladimer
Published: (2025)

Primal: A Unified Deterministic Framework for Quasi-Orthogonal Hashing and Manifold Learning
by: Khasia, Vladimer
Published: (2025)

SLAY: Geometry-Aware Spherical Linearized Attention with Yat-Kernel
by: Luna, Jose Miguel, et al.
Published: (2026)

Probability-Generating Function Kernels for Spherical Data
by: Papamarkou, Theodore, et al.
Published: (2021)

New Bounds for Kernel Sums via Fast Spherical Embeddings
by: Wagner, Tal
Published: (2026)

Neural Operators for Biomedical Spherical Heterogeneity
by: Tang, Hao, et al.
Published: (2026)

Projection-Free Transformers via Gaussian Kernel Attention
by: Kundu, Debarshi, et al.
Published: (2026)

Autoregressive Surrogate Modeling of the Solar Wind with Spherical Fourier Neural Operator
by: Mansouri, Reza, et al.
Published: (2025)

Attention in Geometry: Scalable Spatial Modeling via Adaptive Density Fields and FAISS-Accelerated Kernels
by: Fan, Zhaowen
Published: (2026)

Solving Attention Kernel Regression Problem via Pre-conditioner
by: Song, Zhao, et al.
Published: (2023)

Generalized Spherical Neural Operators: Green's Function Formulation
by: Tang, Hao, et al.
Published: (2025)

Beyond Cross-Validation: Adaptive Parameter Selection for Kernel-Based Gradient Descents
by: Liu, Xiaotong, et al.
Published: (2026)

Beyond Similarity: Temporal Operator Attention for Time Series Analysis
by: Twitty, Jevon, et al.
Published: (2026)

Sparse Attention as Compact Kernel Regression
by: Santos, Saul, et al.
Published: (2026)

Random Features for Operator-Valued Kernels: Bridging Kernel Methods and Neural Operators
by: Nguyen, Mike, et al.
Published: (2026)

FedFrozen: Two-Stage Federated Optimization via Attention Kernel Freezing
by: Du, Junye, et al.
Published: (2026)

Flex Attention: A Programming Model for Generating Optimized Attention Kernels
by: Dong, Juechu, et al.
Published: (2024)

Adaptive Kernel Selection for Kernelized Diffusion Maps
by: Aboussaad, Othmane, et al.
Published: (2026)

IKNO: Infinite-order Kernel Neural Operators
by: Zhu, Pengyuan, et al.
Published: (2026)

Toward Data-Driven Surrogates of the Solar Wind with Spherical Fourier Neural Operator
by: Mansouri, Reza, et al.
Published: (2025)

Diagonal Over-parameterization in Reproducing Kernel Hilbert Spaces as an Adaptive Feature Model: Generalization and Adaptivity
by: Li, Yicheng, et al.
Published: (2025)

AdaKernel: Learning Adaptive Kernel Parameters for Spatiotemporal Graph Neural Networks
by: Zhang, Zhongyue, et al.
Published: (2026)

Kernelized Edge Attention: Addressing Semantic Attention Blurring in Temporal Graph Neural Networks
by: Waghmare, Govind, et al.
Published: (2026)

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond
by: Ke, Yekun, et al.
Published: (2024)

Locally Adaptive Conformal Inference for Operator Models
by: Harris, Trevor, et al.
Published: (2025)

SOCKET: SOft Collision Kernel EsTimator for Sparse Attention
by: Joshi, Sahil, et al.
Published: (2026)

DyKen-Hyena: Dynamic Kernel Generation via Cross-Modal Attention for Multimodal Intent Recognition
by: Wang, Yifei, et al.
Published: (2025)

Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention
by: Huang, Siyuan, et al.
Published: (2024)

Beyond Language Models: Byte Models are Digital World Simulators
by: Wu, Shangda, et al.
Published: (2024)

SVD-NO: Learning PDE Solution Operators with SVD Integral Kernels
by: Koren, Noam, et al.
Published: (2025)

Operator World Models for Reinforcement Learning
by: Novelli, Pietro, et al.
Published: (2024)

Learning Local Causal World Models with State Space Models and Attention
by: Petri, Francesco, et al.
Published: (2025)