Kernel Reboot: Breaking the Boundaries of Neural Tangent Kernels for Neural Fields
cs.LG, cs.CV
Submitted: 2026-09-02
Updated: 2026-09-02
Comments: Published in IEEE TPAMI, vol. 48, no. 9, pp. 10940-10957, Sep. 2026. Author version adds related-work references and biography updates; Figures 12 and 13 were regenerated from the same locked hyperparameter sweep. Tabulated results, reported best points, scientific claims, and conclusions are unchanged
Journal ref: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 48, no. 9, pp. 10940-10957, Sep. 2026
DOI: 10.1109/TPAMI.2026.3692624
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Spatial Functa: Scaling Functa to ImageNet Classification and Generation
- Efficient kernel surrogates for neural network-based regression
- Dataset Distillation Meets Provable Subset Selection
- Enhanced Convolutional Neural Tangent Kernels
- Tensor Programs II: Neural Tangent Kernel for Any Architecture
- How Do the Architecture and Optimizer Affect Representation Learning? On the Training Dynamics of Representations in Deep Neural Networks
- DataS^3: Dataset Subset Selection for Specialization
- Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching
- See Less, Drive Better: Generalizable End-to-End Autonomous Driving via Foundation Models Stochastic Patch Selection
- Robustness Is a Function, Not a Number: A Factorized Comprehensive Study of OOD Robustness in Vision-Based Driving
- Prompts to Summaries: Zero-Shot Language-Guided Video Summarization with Large Language and Video Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks