Performance Analysis
Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense Kalpesh Krishna Yixiao Song Marzena Karpinska John Wieting Mohit Iyyer
API, looking for sequences that match the candidate text within a certain threshold.
Learning Sample Difficulty from Pre-trained Models for Reliable Prediction
Equipped with the knowledge of sample difficulty, we further propose to use it for regularizing the prediction confidence.
4eb33c53ed5b14ce9028309431f565cc-Paper-Datasets_and_Benchmarks.pdf
Does progress on ImageNet transfer to real-world datasets?
MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data
Learning and Deep Graph Neural Networks to learn gene representations from single-cell sequencing and spatial transcriptomic data.
Single-Stage Visual Query Localization in Egocentric Videos
VQL presents a myriad of challenges to existing computer vision systems.
Window-Based Distribution Shift Detection for Deep Neural Networks
Based on this bound, our detector continuously monitors the operation of the network over a test window and fires off an alarm whenever a deviation is detected.
Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation
Extensive experiments and analyses have been conducted to characterize and demonstrate the effectiveness of the proposed DivOE.
Fairly Recommending with Social Attributes: A Flexible and Controllable Optimization Approach
Previous IGF notions only focus on the direct utility of the item exposures, i.e., the exposure numbers across different item groups.