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

[2207.12381] LightX3ECG: A Lightweight and eXplainable Deep Learning System for 3-lead Electrocardiogram Classification

The paper presents LightX3ECG, a lightweight and explainable deep learning system designed for classifying cardiovascular abnormalities u...

[2510.03027] Lightweight Transformer for EEG Classification via Balanced Signed Graph Algorithm Unrolling

This article presents a novel lightweight transformer model for EEG classification, utilizing a balanced signed graph algorithm to enhanc...

[2510.02826] Multi-scale Autoregressive Models are Laplacian, Discrete, and Latent Diffusion Models in Disguise

This paper explores the reinterpretation of Visual Autoregressive Models (VAR) as iterative refinement models, linking them to denoising ...

[2509.23437] Better Hessians Matter: Studying the Impact of Curvature Approximations in Influence Functions

This paper investigates the impact of Hessian approximations on influence functions in deep learning, demonstrating that better approxima...

[2509.20993] Learning the Inverse Temperature of Ising Models under Hard Constraints using One Sample

This paper presents a method for estimating the inverse temperature parameter of truncated Ising models using a single sample, focusing o...

[2509.19189] Functional Scaling Laws in Kernel Regression: Loss Dynamics and Learning Rate Schedules

This article explores Functional Scaling Laws in kernel regression, focusing on loss dynamics and the impact of learning rate schedules, ...

[2509.00955] ART: Adaptive Resampling-based Training for Imbalanced Classification

The paper presents ART, a novel Adaptive Resampling-based Training method for imbalanced classification that dynamically adjusts training...

[2508.11025] Zono-Conformal Prediction: Zonotope-Based Uncertainty Quantification for Regression and Classification Tasks

The paper introduces Zono-Conformal Prediction, a method for uncertainty quantification in regression and classification tasks that impro...

[2508.08326] Weather-Driven Agricultural Decision-Making Using Digital Twins Under Imperfect Conditions

This article explores the use of digital twin technology in agriculture, focusing on its ability to enhance decision-making under imperfe...

[2508.07428] Lightning Prediction under Uncertainty: DeepLight with Hazy Loss

The paper presents DeepLight, a novel deep learning architecture designed for predicting lightning occurrences by addressing the limitati...

[2508.01055] FGBench: A Dataset and Benchmark for Molecular Property Reasoning at Functional Group-Level in Large Language Models

FGBench introduces a dataset for molecular property reasoning at the functional group level, enhancing the capabilities of large language...

[2512.18956] Training Multimodal Large Reasoning Models Needs Better Thoughts: A Three-Stage Framework for Long Chain-of-Thought Synthesis and Selection

This paper presents a three-stage framework, SynSelect, for enhancing the training of multimodal large reasoning models through improved ...

[2507.22554] DeepC4: Deep Conditional Census-Constrained Clustering for Large-scale Multitask Spatial Disaggregation of Urban Morphology

The paper presents DeepC4, a novel deep learning approach for spatial disaggregation of urban morphology, enhancing mapping quality using...

[2511.14853] Uncertainty-Aware Measurement of Scenario Suite Representativeness for Autonomous Systems

This paper presents a probabilistic method to measure the representativeness of scenario suites for autonomous systems, focusing on ensur...

[2507.12549] The Serial Scaling Hypothesis

The article presents the Serial Scaling Hypothesis, which identifies limitations in current parallel computing architectures for inherent...

[2511.11079] ARCTraj: A Dataset and Benchmark of Human Reasoning Trajectories for Abstract Problem Solving

ARCTraj introduces a dataset and framework for modeling human reasoning in abstract problem-solving, providing insights into the iterativ...

[2506.23875] Chain of Thought in Order: Discovering Learning-Friendly Orders for Arithmetic

This article explores the importance of ordering in the chain of thought for Transformers in arithmetic tasks, proposing a method to iden...

[2511.07262] AgenticSciML: Collaborative Multi-Agent Systems for Emergent Discovery in Scientific Machine Learning

The paper introduces AgenticSciML, a multi-agent system designed to enhance scientific machine learning through collaborative reasoning, ...

[2511.06185] Dataforge: Agentic Platform for Autonomous Data Engineering

The article presents Dataforge, an LLM-powered platform designed to automate data engineering processes, enhancing efficiency in preparin...

[2506.22447] Vision Transformers for Multi-Variable Climate Downscaling: Emulating Regional Climate Models with a Shared Encoder and Multi-Decoder Architecture

This article presents a novel multi-variable Vision Transformer architecture for climate downscaling, improving accuracy and efficiency o...