#Data Science
Latest news articles tagged with "Data Science". Follow the timeline of events, related topics, and entities.
Articles (30)
-
🇺🇸 Generative Data Transformation: From Mixed to Unified Data
[USA]
arXiv:2602.22743v1 Announce Type: new Abstract: Recommendation model performance is intrinsically tied to the quality, volume, and relevance of their training data. To address common challenges like ...
Related: #Artificial Intelligence, #Recommendation Systems -
🇺🇸 ConceptRM: The Quest to Mitigate Alert Fatigue through Consensus-Based Purity-Driven Data Cleaning for Reflection Modelling
[USA]
arXiv:2602.20166v1 Announce Type: cross Abstract: In many applications involving intelligent agents, the overwhelming volume of alerts (mostly false) generated by the agents may desensitize users and...
Related: #Artificial Intelligence, #Human-Computer Interaction -
🇺🇸 Uncertainty-Aware Delivery Delay Duration Prediction via Multi-Task Deep Learning
[USA]
arXiv:2602.20271v1 Announce Type: cross Abstract: Accurate delivery delay prediction is critical for maintaining operational efficiency and customer satisfaction across modern supply chains. Yet the ...
Related: #Machine Learning, #Supply Chain Management -
🇺🇸 DS-STAR: Data Science Agent for Solving Diverse Tasks across Heterogeneous Formats and Open-Ended Queries
[USA]
arXiv:2509.21825v4 Announce Type: replace Abstract: While large language models (LLMs) have shown promise in automating data science, existing agents often struggle with the complexity of real-world ...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Drift-Aware Variational Autoencoder-based Anomaly Detection with Two-level Ensembling
[USA]
arXiv:2602.12976v1 Announce Type: cross Abstract: In today's digital world, the generation of vast amounts of streaming data in various domains has become ubiquitous. However, many of these data are ...
Related: #Machine Learning, #Anomaly Detection -
🇺🇸 TA-KAND: Two-stage Attention Triple Enhancement and U-KAN based Diffusion For Few-shot Knowledge Graph Completion
[USA]
arXiv:2512.12182v2 Announce Type: replace Abstract: Knowledge Graphs have become fundamental infrastructure for applications such as intelligent question answering and recommender systems due to thei...
Related: #Knowledge Graphs, #Artificial Intelligence, #Machine Learning -
🇺🇸 Gallup Will No Longer Track Presidential Approval Ratings
[USA]
The monthly poll has been used to measure presidential performance for almost nine decades.
Related: #Politics, #Media -
🇺🇸 ArcMark: Multi-bit LLM Watermark via Optimal Transport
[USA]
arXiv:2602.07235v1 Announce Type: cross Abstract: Watermarking is an important tool for promoting the responsible use of language models (LMs). Existing watermarks insert a signal into generated toke...
Related: #Artificial Intelligence, #Cybersecurity -
🇺🇸 Exactly Computing do-Shapley Values
[USA]
arXiv:2602.07203v1 Announce Type: cross Abstract: Structural Causal Models (SCM) are a powerful framework for describing complicated dynamics across the natural sciences. A particularly elegant way o...
Related: #Artificial Intelligence, #Mathematics -
🇺🇸 Multimodal Enhancement of Sequential Recommendation
[USA]
arXiv:2602.07207v1 Announce Type: cross Abstract: We propose a novel recommender framework, MuSTRec (Multimodal and Sequential Transformer-based Recommendation), that unifies multimodal and sequentia...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Beyond Pooling: Matching for Robust Generalization under Data Heterogeneity
[USA]
arXiv:2602.07154v1 Announce Type: cross Abstract: Pooling heterogeneous datasets across domains is a common strategy in representation learning, but naive pooling can amplify distributional asymmetri...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Hybrid Deep Learning Framework for CSI-Based Activity Recognition in Bandwidth-Constrained Wi-Fi Sensing
[USA]
arXiv:2602.06983v1 Announce Type: cross Abstract: This paper presents a novel hybrid deep learning framework designed to enhance the robustness of CSI-based Human Activity Recognition (HAR) within ba...
Related: #Artificial Intelligence, #Wireless Technology -
🇺🇸 Data Science and Technology Towards AGI Part I: Tiered Data Management
[USA]
arXiv:2602.09003v1 Announce Type: new Abstract: The development of artificial intelligence can be viewed as an evolution of data-driven learning paradigms, with successive shifts in data organization...
Related: #Artificial Intelligence, #Technology -
🇺🇸 CausalT5K: Diagnosing and Informing Refusal for Trustworthy Causal Reasoning of Skepticism, Sycophancy, Detection-Correction, and Rung Collapse
[USA]
arXiv:2602.08939v1 Announce Type: new Abstract: LLM failures in causal reasoning, including sycophancy, rung collapse, and miscalibrated refusal, are well-documented, yet progress on remediation is s...
Related: #Artificial Intelligence, #Logic and Reasoning -
🇺🇸 Deciding the Satisfiability of Combined Qualitative Constraint Networks
[USA]
arXiv:2602.08848v1 Announce Type: new Abstract: Among the various forms of reasoning studied in the context of artificial intelligence, qualitative reasoning makes it possible to infer new knowledge ...
Related: #Artificial Intelligence, #Computational Logic -
🇺🇸 Negative-Aware Diffusion Process for Temporal Knowledge Graph Extrapolation
[USA]
arXiv:2602.08815v1 Announce Type: new Abstract: Temporal Knowledge Graph (TKG) reasoning seeks to predict future missing facts from historical evidence. While diffusion models (DM) have recently gain...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Exploring SAIG Methods for an Objective Evaluation of XAI
[USA]
arXiv:2602.08715v1 Announce Type: new Abstract: The evaluation of eXplainable Artificial Intelligence (XAI) methods is a rapidly growing field, characterized by a wide variety of approaches. This div...
Related: #Artificial Intelligence, #Technology Research -
🇺🇸 From Out-of-Distribution Detection to Hallucination Detection: A Geometric View
[USA]
arXiv:2602.07253v1 Announce Type: new Abstract: Detecting hallucinations in large language models is a critical open problem with significant implications for safety and reliability. While existing h...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Effect-Level Validation for Causal Discovery
[USA]
arXiv:2602.08340v1 Announce Type: new Abstract: Causal discovery is increasingly applied to large-scale telemetry data to estimate the effects of user-facing interventions, yet its reliability for de...
Related: #Machine Learning, #Causality -
🇺🇸 Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning
[USA]
arXiv:2602.07830v1 Announce Type: new Abstract: Time series is a pervasive data type across various application domains, rendering the reasonable solving of diverse time series tasks a long-standing ...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 EventCast: Hybrid Demand Forecasting in E-Commerce with LLM-Based Event Knowledge
[USA]
arXiv:2602.07695v1 Announce Type: new Abstract: Demand forecasting is a cornerstone of e-commerce operations, directly impacting inventory planning and fulfillment scheduling. However, existing forec...
Related: #Artificial Intelligence, #E-commerce -
🇺🇸 Efficient Table Retrieval and Understanding with Multimodal Large Language Models
[USA]
arXiv:2602.07642v1 Announce Type: new Abstract: Tabular data is frequently captured in image form across a wide range of real-world scenarios such as financial reports, handwritten records, and docum...
Related: #Artificial Intelligence, #Technology -
🇺🇸 Disentangled Instrumental Variables for Causal Inference with Networked Observational Data
[USA]
arXiv:2602.07765v1 Announce Type: new Abstract: Instrumental variables (IVs) are crucial for addressing unobservable confounders, yet their stringent exogeneity assumptions pose significant challenge...
Related: #Causal Inference, #Artificial Intelligence -
🇺🇸 Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training
[USA]
arXiv:2602.07824v1 Announce Type: new Abstract: Data quality determines foundation model performance, yet systematic processing frameworks are lacking. We introduce Data Darwinism, a ten-level taxono...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 IV Co-Scientist: Multi-Agent LLM Framework for Causal Instrumental Variable Discovery
[USA]
arXiv:2602.07943v1 Announce Type: new Abstract: In the presence of confounding between an endogenous variable and the outcome, instrumental variables (IVs) are used to isolate the causal effect of th...
Related: #Artificial Intelligence, #Causal Inference -
🇺🇸 Structure-Aware Robust Counterfactual Explanations via Conditional Gaussian Network Classifiers
[USA]
arXiv:2602.08021v1 Announce Type: new Abstract: Counterfactual explanation (CE) is a core technique in explainable artificial intelligence (XAI), widely used to interpret model decisions and suggest ...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Towards Better Evolution Modeling for Temporal Knowledge Graphs
[USA]
arXiv:2602.08353v1 Announce Type: new Abstract: Temporal knowledge graphs (TKGs) structurally preserve evolving human knowledge. Recent research has focused on designing models to learn the evolution...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Reinforcement Inference: Leveraging Uncertainty for Self-Correcting Language Model Reasoning
[USA]
arXiv:2602.08520v1 Announce Type: new Abstract: Modern large language models (LLMs) are often evaluated and deployed under a \emph{one-shot, greedy} inference protocol, especially in professional set...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models
[USA]
arXiv:2602.07026v1 Announce Type: cross Abstract: Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modalit...
Related: #Artificial Intelligence, #Machine Learning -
🇺🇸 MTS-CSNet: Multiscale Tensor Factorization for Deep Compressive Sensing on RGB Images
[USA]
arXiv:2602.07056v1 Announce Type: cross Abstract: Deep learning based compressive sensing (CS) methods typically learn sampling operators using convolutional or block wise fully connected layers, whi...
Related: #Artificial Intelligence, #Signal Processing