Tag
REALMS is a conversational AI system for real-time exact audience sizing using LLMs and embeddings, enabling marketers to query high-dimensional profile data with natural language and receive precise counts quickly in production.
This paper introduces a novel semi-tensor product for tensors and develops a multi-term randomized tensor singular value decomposition (MSTP-SVD) to improve low-rank approximation accuracy and computational efficiency for visual data processing tasks.
FloDR is a dimensionality reduction method based on a normalising flow that creates an invertible embedding, preserving both local and global structure while providing diagnostic tools like conditional spread and hidden contrast.
This paper introduces GOTabPFN, a method that combines Graph-guided Ordering with Local Refinement (GO-LR) and Neuro-Inspired Subunit Compression (NSC) to make small tabular foundation models effective for high-dimensional, low-sample-size prediction without retraining large backbones.
AdaGraph is a graph-native clustering algorithm that operates within the kNN graph topology to overcome the curse of dimensionality, validated across genomics, NLP, and materials science domains via the Structure-Centric Machine Learning paradigm.
RSNet is an open-source R package that provides a resampling-based framework for robust and interpretable network inference in high-dimensional data, supporting partial correlation networks and conditional Gaussian Bayesian networks with graphlet-based topology analysis.