ROC-AUC
PulseAugur coverage of ROC-AUC — every cluster mentioning ROC-AUC across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
Hybrid Gossip-FedAvg shows promise in decentralized histopathology image classification
Researchers have compared three distributed learning methods for histopathology image classification: server-based Federated Averaging (FedAvg), decentralized gossip learning, and a hybrid approach combining both. Using…
-
AI framework and benchmark advance nanomedicine discovery
Researchers have introduced NSA-Bench, the first public benchmark designed to standardize the evaluation of nano self-assembly prediction for nanomedicine discovery. They also developed NSA-Net, a multimodal framework t…
-
New research models turn-taking dynamics in multi-party conversations
Two new research papers explore the dynamics of multi-party conversations, focusing on how turn-taking and conversational cues can be modeled and predicted. The first paper introduces a multi-task learning approach that…
-
New DTD-VAE model enhances credit risk prediction by disentangling temporal data
Researchers have developed a new variational autoencoder model called DTD-VAE, designed to improve credit risk prediction by disentangling temporal dependencies in customer data. This model distinguishes between pattern…
-
ML cough models fail to generalize for TB screening, study finds
A new study evaluating machine learning models for tuberculosis screening using cough acoustics found that despite strong within-dataset performance, these models fail to generalize to new datasets. The research indicat…
-
New system predicts lithium-ion battery thermal runaway using infrared hotspots
Researchers have developed a novel two-stage early-warning system to detect thermal runaway in lithium-ion batteries, particularly under mechanical stress. The system leverages infrared hotspot dynamics to estimate loca…
-
New method corrects seasonal false alarms in customer churn prediction
A new research paper published on arXiv addresses a critical issue in customer churn prediction systems, where seasonal fluctuations can lead to false alarms. The study proposes a year-over-year correction method to dif…
-
New diagnostic tool assesses LLM judge effectiveness without external verification
Researchers have developed a new method to evaluate the effectiveness of Large Language Model (LLM) judges used in skill optimization tasks. The proposed diagnostic, termed a "reference-free judge," assesses whether an …
-
New AI agents show predictive allostatic organization in simulations
Researchers have developed recurrent and spiking agents capable of adaptive behavior under partial observability, drawing inspiration from Barrett and Miller's theory of categorization. These agents were tested in an en…
-
AI model reduces need for spine degeneration grading labels via segmentation pre-training
Researchers have developed a new method for grading lumbar spine degeneration using segmentation pre-training, which significantly reduces the need for expert-annotated radiological gradings. By pre-training a 3D ResNet…
-
Federated generative models show promise for electronic health records
Researchers have developed federated generative event models (GEMs) for tokenized electronic health records, addressing data silos and performance degradation across different health systems. In an evaluation across thr…
-
Evo 2 DNA model identifies AMR genes with high accuracy
A new lightweight probe, Evo 2, has been developed to detect antimicrobial resistance (AMR) genes directly from raw metagenomic data. This method bypasses the need for expensive genome assembly steps, achieving a high a…
-
New benchmarks and datasets advance deepfake detection for audio, image, and video
Researchers have introduced several new datasets and benchmarks aimed at improving the detection of deepfakes across various media. Echoes focuses on music deepfakes, emphasizing semantic alignment and provider diversit…
-
Graph Neural Networks applied to optimization and physics problems · 2 sources tracked
Researchers are exploring the application of graph neural networks (GNNs) beyond their traditional roles in combinatorial optimization and theoretical physics. One study demonstrates that GNNs can function as effective …
-
Research paper identifies key metrics for brain-computer interface spelling accuracy
This research paper investigates which performance metrics best correlate with the spelling rate accuracy in event-related potential (ERP)-based brain-computer interfaces (BCIs). The study analyzed 13 metrics across two…
-
AI models detect clinical trial dosing errors with high accuracy · 2 sources tracked
Researchers have developed a method to detect dosing errors in clinical trials using domain-specific transformer embeddings and classification models. The study evaluated several language models, including ClinicalBERT,…
-
New GMM pooling method enhances preterm birth prediction from ultrasound images
Researchers have developed a new Gaussian Mixture Model (GMM) pooling method for multiple instance learning (MIL) to improve preterm birth prediction from ultrasound images. This approach models the feature distribution…