Tag
This paper introduces KODA (Kernel Optimization for Discrepancy Analysis), a kernel-based framework for comparing and aligning vision-language model representations by identifying sample subsets that are clustered differently across models like CLIP, SigLIP, and BLIP. The method uses contrastive embedding clustering and randomized low-dimensional approximations to scale to large datasets while providing interpretable structural differences between representations.
This paper introduces a distributional generalization of matrix completion where each entry is a probability distribution rather than a scalar, using kernel mean embeddings and Tucker rank to capture low-rank structure. The authors propose a novel estimator with non-asymptotic error bounds and demonstrate effectiveness on synthetic and real-world data.
Researchers from MIT, University of Warwick, and NVIDIA introduce Stein Kernelized Molecular Dynamics (SKMD), an enhanced sampling method that uses interacting particle dynamics to acquire informative training configurations for active learning and fine-tuning of machine learning interatomic potentials (MLIPs). SKMD is a stochastic variant of Stein variational gradient descent adapted for molecular dynamics, preserving the Boltzmann distribution while achieving higher model accuracy in fewer training iterations compared to baselines.
Introduces a perturbative approach for nonparametric instrumental variable estimation that extends kernel ridge methods with higher-order corrections, achieving up to 99% reduction in prediction error in high-dimensional settings.
Proposes Interdomain Attention, a new method that integrates state space models into attention via kernel methods, achieving efficient long-context modeling with a fixed-size state and outperforming SSMs and softmax attention in language modeling experiments up to 1.3B parameters.
This paper decomposes the predictive KL divergence between Gaussian process and latent neural process posteriors into three terms, providing upper bounds that characterize approximation errors and connecting representation dimension to kernel smoothness.
This paper proposes a hybrid quantum-classical workflow for plant phenomics classification under small-data regimes, using supervised latent restructuring (PCA + LDA) to improve geometric separability before quantum kernel alignment. Experiments show improved separability but highlight compression trade-offs and the difficulty of achieving strong quantum performance.