Auroc
PulseAugur coverage of Auroc — every cluster mentioning Auroc across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
AI model predicts AML mutations from flow cytometry data
Researchers have developed an interpretable multi-instance learning model that can predict key molecular alterations in acute myeloid leukemia (AML) from routine flow cytometry data. This approach, which models patient …
-
Small LLMs like Qwen2.5 and Llama 3.2 exhibit significant capitulation to user pushback
A new research paper investigates the tendency of small language models, specifically Qwen2.5-1.5B and Llama-3.2-1B, to abandon correct answers when challenged by users. The study found that these models frequently swit…
-
New research questions VLM confidence calibration, proposes new evaluation metric
A new research paper published on arXiv, "The Mirage of Calibrated Confidence," reveals that vision-language models (VLMs) often report high confidence in their answers regardless of the reasoning process they followed.…
-
Knowledge-enriched EHR features offer efficient hospital readmission prediction
Researchers have developed a new method for predicting 30-day hospital readmissions using structured Electronic Health Record (EHR) data augmented with medical knowledge sources. This approach avoids the need for clinic…
-
New XConf method estimates LLM confidence using past experiences
Researchers have introduced XConf, a novel method for estimating the confidence of language model outputs by incorporating the model's past experiences. Unlike existing methods that only consider the current inference p…
-
New OAS-MIL framework predicts cancer risk from MRI scans · 2 sources tracked
Researchers have developed a weakly supervised framework called Order-Aware Slab Multiple Instance Learning (OAS-MIL) to predict the risk of perineural invasion (PNI) in intrahepatic cholangiocarcinoma (ICC) using preop…
-
New VFR-Audit framework enhances reliability of AI fairness audits
Researchers have introduced VFR-Audit, a new framework designed to assess the reliability of fairness audits in clinical AI applications, specifically for predicting hospital length-of-stay. This framework focuses on th…
-
Under-mattress sensors predict dementia patient agitation risk
Researchers have developed a method using under-mattress sensors to predict agitation risk in dementia patients the following day. The study found that minute-level temporal modeling of overnight physiological signals, …
-
New segmentation models show promise for tracking eye disease lesions
Researchers have developed and evaluated four lesion-segmentation pipelines, including 2D and 3D variants for AMD and DME, achieving Dice scores between 0.76 and 0.82 on an in-domain validation set. These pipelines demo…
-
New research tackles video anomaly detection with causal models and improved evaluation
Researchers are exploring new methods for video anomaly detection, focusing on improving efficiency and accuracy. One paper introduces a strictly causal streaming anomaly detector using a Mamba-style state-space model t…
-
LeakGauge detector flags AI context-leakage attacks with 0.996 AUROC
A new detector called LeakGauge has been introduced in an arXiv preprint, designed to identify instances where large language models leak confidential context. The tool has demonstrated high effectiveness, achieving an …
-
FedCoRe framework tackles missing data in healthcare federated learning
Researchers have developed FedCoRe, a novel framework for federated learning in healthcare that addresses the challenge of missing data modalities. FedCoRe learns to correct for missing information, such as ECGs or ches…
-
Vision Transformer Detects Heart Condition from ECGs with High Accuracy
Researchers have developed a vision transformer model capable of detecting reduced left ventricular ejection fraction (LVEF) from standard electrocardiograms (ECGs). The model, trained on over 10,000 patients across mul…
-
AI system enhances quality assurance for breast MRI datasets
Researchers have developed an unsupervised anomaly detection system to ensure the quality of multi-center breast MRI datasets used for medical AI. The system addresses the critical need for robust dataset quality assura…
-
New EGRL framework improves RNA-protein interaction prediction
Researchers have developed a new framework called EGRL for predicting RNA-protein interactions (RPIs), which are crucial for cellular functions. This deep learning approach utilizes graph neural networks to model RPI ne…
-
New framework SymboUQ improves LLM spatial reasoning reliability
Researchers have introduced SymboUQ, a novel framework designed to enhance the reliability of spatial reasoning in large language models (LLMs). This system quanties uncertainty by assessing whether claims can be symbol…
-
New ML framework enhances drug discovery screening metrics
Researchers have developed a new machine learning framework to improve performance metric estimation in high-throughput screening (HTS) assays, which are crucial for early-stage drug discovery. The framework addresses t…
-
New framework tackles bias in adaptive data cleaning methods
A new evaluation framework has been developed to address confounding biases in adaptive data cleaning methods. These methods, which use data-driven partitions instead of manual thresholds, can implicitly alter performan…
-
SkillTrace achieves 0.938 AUROC in auditing LLM agent skill reuse
SkillTrace, a new auditing tool, has demonstrated a high level of effectiveness in detecting the reuse of skills within large language model (LLM) agents. The system achieves an AUROC score of 0.938 by analyzing three d…
-
New AI frameworks learn from cellular phenotypes and transcriptomic data
Two new research papers propose advanced methods for learning representations from biological data. The first, PhenMol, focuses on preserving molecular structure while learning from cellular phenotypes for drug discover…