Claims Browser

Existing graph anomaly detection approaches insufficiently utilize node labels

"they insufficiently utilize node labels for GAD"

The proposed JPGFN method significantly outperforms mainstream graph anomaly detection approaches on multiple real-world datasets

"Experimental results on multiple real-world datasets demonstrate that the proposed method significantly outperforms mainstream approaches."

FiUni can effectively infer latent batch-level task affiliations and achieve competitive performance against advanced task-aware continual learning methods with fewer trainable parameters

"Experiments show that FiUni can effectively infer latent batch-level task affiliations and achieve competitive performance against advanced task-aware CL methods with fewer trainable parameters."

FiUni's approach of constructing FIM-derived frozen subspaces to guide low-rank adaptation while matching Fisher principal subspaces enables adaptive determination of whether to reuse knowledge, expand subspaces, or create new ones, dynamically balancing knowledge sharing and task isolation

"FiUni constructs FIM-derived frozen subspaces to guide low-rank adaptation (LoRA), while matching the Fisher principal subspace of each incoming batch window with historical subspaces. This enables FiUni to adaptively determine whether to reuse existing knowledge, expand a related subspace, or create a new subspace, dynamically balancing knowledge sharing and task isolation."

Nvidia is acquiring Hugging Face for $12.9 billion

"Nvidia is buying Hugging Face for $12.9B (via The Information)."

A retrieval-augmented few-shot prompting pipeline with Qwen2.5-14B-Instruct achieves 0.8692 Semantic Graph Similarity and 0.9200 Term-Typing F1 on the ontology extension task

"The approach achieves Semantic Graph Similarity of 0.8692, Term-Typing F1 of 0.9200, and Taxonomy Discovery F1 of 0.8540 on Task B"

A class-level automated multi-objective search-based system using SPEA-2 achieved higher precision and recall than NSGA-II and MOEA/D for bug localization

"Results indicate that SPEA-2 achieved higher precision and recall than both multi-objective and single-objective baseline methods."

The bug localization recommender system successfully identified buggy classes for 88.5% of bug reports within the top 10 recommendations and 94% within the top 20

"The proposed recommender system successfully identified buggy classes or files for 88.5\% of bug reports within the top 10 recommendations and 94\% within the top 20."

The multi-objective bug localization model demonstrates adaptability across programming languages, validated on both Java and Kotlin projects

"The effectiveness of the model was further validated on an industrial Android project written in Kotlin, demonstrating its adaptability across programming languages."

Relying solely on lexical similarity between source code and bug reports is often insufficient for bug localization due to the natural language nature of bug descriptions

"In addition, relying solely on lexical similarity between source code and bug reports is often insufficient due to the natural language nature of bug descriptions."

Deep learning segmentation models for OCT typically fail to generalize to clinical data collected under different acquisition protocols

"Most deep-learning segmentation work for OCT is validated only in-domain, leaving generalization to clinical data collected under different acquisition protocols largely untested."

The developed AMD and DME lesion-segmentation pipelines achieve Dice scores between 0.76 and 0.82 with strong calibration on in-domain validation

"reaching Dice scores of 0.76 to 0.82 with strong volumetric and surface calibration (r vol, r surf greater than or equal to 0.97 across all four pipelines) on an in-domain validation set"

Ensemble composition is the most consistent driver of improvement in OCT lesion segmentation models

"identifies ensemble composition as the most consistent driver of improvement"

Automated lesion-burden tracking shows promise but is not yet validated as a clinical tool, with predictions tracking biomarkers less strongly out-of-domain than in-domain

"Predictions track clinical biomarkers outside the training distribution, though less strongly than in-domain -- evidence for, not validation of, automated lesion-burden tracking as a clinical tool."

Ontology learning from text remains challenging despite significant progress in Large Language Models

"Ontology learning from text remains challenging despite significant progress in Large Language Models (LLMs)"

LLMs favor hierarchical relations over associative relations in ontology learning tasks

"favor hierarchical over associative relations"

Current LLM-based ontology learning systems fail to extract non-taxonomic relations due to limitations of closed, taxonomy-oriented relation vocabularies

"However, no non-taxonomic relations are extracted, highlighting limitations of closed, taxonomy-oriented relation vocabularies"

Graph anomaly detection methods based on frequency-domain filtering have achieved promising results in recent years

"In recent years, graph anomaly detection (GAD) based on frequency-domain filtering have achieved promising results."

Existing graph anomaly detection approaches use static basic functions for graph filters which cannot effectively adapt to frequency-domain distribution of graph data

"they use static basic function to constructed graph filter which cannot effectively adapt to the frequency-domain distribution of graph data"