BioCon is the first benchmark dataset and cross-modal framework for detecting inconsistencies between methodological descriptions in bioinformatics papers and their code implementations.
Focal loss for dense object detection
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
ReDef creates a revert-anchored dataset of 3,164 defective and 10,268 clean code modifications and shows that code language models perform better with diff encodings but maintain stable performance under counterfactual perturbations, indicating reliance on superficial cues.
DART is a cross-modal foundation model that delivers rope damage classification, severity regression, and few-shot recognition from a single frozen representation trained on 4270 images across 14 damage classes.
The ADC method automates the creation of large image classification datasets using LLMs and search engines, achieving 79% human agreement and reducing label noise on a 1 million image clothing dataset, while also releasing benchmarks for noise and bias issues.
Feature sharing embedded in every stage of Cascade R-CNN narrows the low-IoU gap, improves all thresholds, and reaches 43.2 AP on COCO with negligible added parameters.
citing papers explorer
-
Do Papers Tell the Whole Story? A Benchmark and Framework for Uncovering Hidden Implementation Gaps in Bioinformatics
BioCon is the first benchmark dataset and cross-modal framework for detecting inconsistencies between methodological descriptions in bioinformatics papers and their code implementations.
-
ReDef: Do Code Language Models Truly Understand Code Changes for Just-in-Time Software Defect Prediction?
ReDef creates a revert-anchored dataset of 3,164 defective and 10,268 clean code modifications and shows that code language models perform better with diff encodings but maintain stable performance under counterfactual perturbations, indicating reliance on superficial cues.
-
DART: A Vision-Language Foundation Model for Comprehensive Rope Condition Monitoring
DART is a cross-modal foundation model that delivers rope damage classification, severity regression, and few-shot recognition from a single frozen representation trained on 4270 images across 14 damage classes.
-
Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond
The ADC method automates the creation of large image classification datasets using LLMs and search engines, achieving 79% human agreement and reducing label noise on a 1 million image clothing dataset, while also releasing benchmarks for noise and bias issues.
-
Rethinking Classification and Localization for Cascade R-CNN
Feature sharing embedded in every stage of Cascade R-CNN narrows the low-IoU gap, improves all thresholds, and reaches 43.2 AP on COCO with negligible added parameters.