Data Science

Google quietly launched an AI dictation app that works offline

Google's new offline-first dictation app uses Gemma AI models to take on the apps like Wispr Flow.

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...

CONESTOGA COLLEGE Robots deepen AI and data analytics training for Conestoga students

[2506.17047] Navigating the Deep: End-to-End Extraction on Deep Neural Networks

This article presents a novel end-to-end model extraction method for deep neural networks, addressing limitations in existing techniques ...

[2505.24205] On the Expressive Power of Mixture-of-Experts for Structured Complex Tasks

This paper explores the expressive power of Mixture-of-Experts (MoEs) in modeling complex tasks, demonstrating their efficiency in approx...

[2505.12707] PLAICraft: Large-Scale Time-Aligned Vision-Speech-Action Dataset for Embodied AI

PLAICraft introduces a large-scale dataset capturing time-aligned vision, speech, and action data from multiplayer Minecraft, aimed at ad...

[2505.10992] ReaCritic: Reasoning Transformer-based DRL Critic-model Scaling For Wireless Networks

The paper presents ReaCritic, a novel reasoning transformer-based critic model for deep reinforcement learning (DRL) in heterogeneous wir...

[2510.18318] Earth AI: Unlocking Geospatial Insights with Foundation Models and Cross-Modal Reasoning

The paper presents Earth AI, a novel approach to geospatial analysis using foundation models and cross-modal reasoning to derive insights...

[2502.09683] Channel Dependence, Limited Lookback Windows, and the Simplicity of Datasets: How Biased is Time Series Forecasting?

This article examines the biases in time series forecasting (TSF) due to arbitrary lookback windows and channel dependence, advocating fo...

[2502.07274] Forget Forgetting: Continual Learning in a World of Abundant Memory

The paper explores continual learning (CL) in AI, proposing a shift from minimizing memory usage to leveraging abundant memory while addr...

[2509.24803] TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models

The paper introduces TimeOmni-1, a model designed to enhance complex reasoning with time series data in large language models, addressing...

[2409.04332] Amortized Bayesian Workflow

The paper presents an Amortized Bayesian Workflow that combines fast amortized inference with accurate MCMC techniques, optimizing Bayesi...

[2507.03267] GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning

The paper presents GDGB, a benchmark for Generative Dynamic Text-Attributed Graph Learning, addressing the limitations of existing datase...

[2602.16696] Parameter-free representations outperform single-cell foundation models on downstream benchmarks

This paper demonstrates that parameter-free representations can outperform single-cell foundation models in various benchmarks, suggestin...

[2503.16191] Large Language Models for Water Distribution Systems Modeling and Decision-Making

This article discusses the integration of Large Language Models (LLMs) into water distribution system management, introducing LLM-EPANET,...

[2602.16690] Synthetic-Powered Multiple Testing with FDR Control

The paper presents SynthBH, a novel method for multiple hypothesis testing that integrates synthetic data to enhance statistical inferenc...

[2602.16688] On the Hardness of Approximation of the Fair k-Center Problem

This paper addresses the NP-hardness of approximating the fair k-center problem, proving that achieving a (3-ε)-approximation is impossib...

[2502.01160] Scalable Precise Computation of Shannon Entropy

This paper presents a scalable tool, PSE, for precise computation of Shannon entropy, optimizing the process to enhance efficiency in qua...

[2411.06624] A Review of Fairness and A Practical Guide to Selecting Context-Appropriate Fairness Metrics in Machine Learning

This article reviews fairness in machine learning, emphasizing the need for context-appropriate fairness metrics and providing a flowchar...

[2602.16703] Measuring Mid-2025 LLM-Assistance on Novice Performance in Biology

This study evaluates the impact of large language models (LLMs) on novice performance in biology laboratory tasks, revealing modest benef...

[2602.16656] Investigating Nonlinear Quenching Effects on Polar Field Buildup in the Sun Using Physics-Informed Neural Networks

This article explores the nonlinear quenching effects on polar field buildup in the Sun using Physics-Informed Neural Networks (PINN), hi...

[2602.16650] Retrieval Augmented Generation of Literature-derived Polymer Knowledge: The Example of a Biodegradable Polymer Expert System

This article presents a novel approach to extracting polymer knowledge from literature using Retrieval-Augmented Generation (RAG) techniq...

[2602.16634] Enhanced Diffusion Sampling: Efficient Rare Event Sampling and Free Energy Calculation with Diffusion Models

The paper presents Enhanced Diffusion Sampling, a novel method for efficient rare event sampling and free energy calculation in molecular...