This paper proposes PairGS, a framework for open-vocabulary 3D Gaussian segmentation that models pairwise relations between Gaussians using rich signals from 3D Gaussian representations.

The paper proposes WEINCE, a modified InfoNCE objective that uses extreme value theory corrections to improve contrastive learning by more accurately modeling the selection of hard negative examples.

HASTE introduces group-shared fixed fan-in sparsity for multi-label classification, achieving significant wall-clock speedups (up to 25x in backward pass) by enabling efficient GPU execution while mai…

The paper introduces trust functions to filter weak supervision labels, enabling near-lossless weak-to-strong generalization by selectively training a strong student using only the most reliable weak…

The paper proves a stochastic comparison for Gaussian maxima, resolving the Weak Simplex Conjecture and proving the Simplex Mean Width Conjecture.

A new boosting algorithm that strong learns concept classes closed under O(log 1/γ)-XOR using O(log 1/ε) calls to a γ-advantage weak learner and additional samples, by connecting boosting with list-de…

GiPL proposes a novel two-branch framework combining iterative pseudo-label self-training and generative data augmentation to significantly improve Cross-Domain Few-Shot Object Detection by better uti…

The paper proposes a robust, multi-stage pipeline combining rule-based classification and machine learning to map noisy retail product names to standardized consumption categories, finding that simple…

This paper introduces CuBAS, an adaptive data selection method for supervised classification based on curvature estimation from a labeled dataset using the Potts MRF model.

This paper provides explicit error bounds for the infinite-width Gaussian-process limit of random neural networks using tensor programs and quantitative convergence theory in Wasserstein distance.

The paper proposes a Signed Entropy Integral (SEI) statistic to detect mislabeled images in training datasets by analyzing the temporal trend of prediction entropy, achieving state-of-the-art results…

This paper proposes methods to improve the encoding capacity and disentanglement of Variational Autoencoders (VAE) by imposing entropy-based constraints and a weight-filter method.

FedMPT introduces a novel federated learning framework for Multi-Label Recognition (MLR) using Vision-Language Models (VLMs) by leveraging generalizable conditions to mitigate label overfitting and im…

This paper introduces survey sampling techniques to estimate or minimize empirical pairwise loss functions, showing that targeting informative pairs significantly reduces computational cost while main…

GJDNet proposes a joint disentanglement framework to enhance the robustness of Graph Neural Networks against adversarial attacks by simultaneously stabilizing node representations and decision boundar…

This paper develops a framework for identifying and estimating parameters of interest in automatic debiased machine learning using a Riesz representer, which is identified when it uniquely optimizes a…