Data Science

UMKC Announces New Master of Science in Artificial Intelligence

UMKC announces a new Master of Science in Artificial Intelligence program aimed at addressing workforce demand for AI expertise, set to l...

Accelerating science with AI and simulations

MIT Professor Rafael Gómez-Bombarelli discusses the transformative potential of AI in scientific research, emphasizing its role in materi...

Scientists uncover new method to generate protein datasets for training AI

[2506.15715] NeuronSeek: On Stability and Expressivity of Task-driven Neurons

The paper introduces NeuronSeek, a framework that enhances the stability and expressivity of task-driven neurons in deep learning through...

[2510.20102] Human-Centered LLM-Agent System for Detecting Anomalous Digital Asset Transactions

The paper presents HCLA, a human-centered multi-agent system designed for detecting anomalies in digital asset transactions, enhancing in...

[2506.12362] HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs

The paper presents HYPER, a foundation model designed for inductive link prediction using knowledge hypergraphs, capable of generalizing ...

[2506.07272] A Cramér-von Mises Approach to Incentivizing Truthful Data Sharing

This paper introduces a novel approach using the Cramér-von Mises statistic to create incentive mechanisms that promote truthful data sha...

[2505.19712] On the Relation between Rectified Flows and Optimal Transport

This paper explores the relationship between rectified flows and optimal transport, highlighting invariance properties and counterexample...

[2505.15008] Know When to Abstain: Optimal Selective Classification with Likelihood Ratios

The paper discusses optimal selective classification using likelihood ratios, enhancing predictive model reliability by allowing abstenti...

[2508.08500] Large Language Models as Oracles for Ontology Alignment

This article explores the use of Large Language Models (LLMs) as tools for improving ontology alignment, demonstrating their effectivenes...

[2505.11771] Residual Feature Integration is Sufficient to Prevent Negative Transfer

This paper presents a novel approach to prevent negative transfer in transfer learning by integrating residual features from pretrained m...

[2505.10271] RainPro-8: An Efficient Deep Learning Model to Estimate Rainfall Probabilities Over 8 Hours

RainPro-8 is a novel deep learning model designed for high-resolution rainfall probability forecasting over an 8-hour horizon, integratin...

[2504.20426] RV-Syn: Rational and Verifiable Mathematical Reasoning Data Synthesis based on Structured Function Library

The paper introduces RV-Syn, a novel approach for synthesizing high-quality mathematical reasoning data using structured function librari...

[2505.06795] Sparse Latent Factor Forecaster (SLFF) with Iterative Inference for Transparent Multi-Horizon Commodity Futures Prediction

The Sparse Latent Factor Forecaster (SLFF) proposes a new approach for predicting commodity futures by addressing forecast errors and enh...

[2505.04338] Riemannian Denoising Diffusion Probabilistic Models

The paper introduces Riemannian Denoising Diffusion Probabilistic Models (RDDPMs), which enhance generative modeling on submanifolds of E...

[2411.06403] Mastering NIM and Impartial Games with Weak Neural Networks: An AlphaZero-inspired Multi-Frame Approach

This paper explores the application of weak neural networks in mastering impartial games like NIM, utilizing an AlphaZero-inspired multi-...

[2504.06193] Heuristic Methods are Good Teachers to Distill MLPs for Graph Link Prediction

This article explores the effectiveness of heuristic methods in distilling Multi-Layer Perceptrons (MLPs) for graph link prediction, reve...

[2503.09411] Learning Rate Annealing Improves Tuning Robustness in Stochastic Optimization

This article explores the advantages of learning rate annealing in stochastic optimization, demonstrating its robustness against initial ...

[2503.01884] Contextual Quantum Neural Networks for Stock Price Prediction

This article presents a novel approach using contextual quantum neural networks for predicting stock prices, enhancing accuracy and effic...

[2502.14560] Less is More: Improving LLM Alignment via Preference Data Selection

This article discusses a novel approach to improving large language model (LLM) alignment through effective preference data selection, en...

[2502.10295] Fenchel-Young Variational Learning

The paper introduces Fenchel-Young variational learning, a new class of variational methods that generalizes classical approaches, enhanc...

[2502.01594] Faster Adaptive Optimization via Expected Gradient Outer Product Reparameterization

This article presents a novel reparameterization method for adaptive optimization algorithms, enhancing their convergence properties thro...

[2501.16178] SWIFT: Mapping Sub-series with Wavelet Decomposition Improves Time Series Forecasting

The paper presents SWIFT, a lightweight model that enhances time series forecasting using wavelet decomposition, achieving state-of-the-a...