NCD Method
NCD methods encompass a broad range of techniques designed to analyze and process complex data, primarily focusing on improving efficiency and accuracy in various applications. Current research emphasizes the development and application of deep learning models, including graph neural networks and transformer architectures, to address challenges in areas such as image and video processing, natural language understanding, and time series analysis. These advancements are significantly impacting fields like healthcare (e.g., medical image analysis and report generation), agriculture (disease detection), and engineering (prognostics and health management), by enabling more efficient and accurate data analysis and decision-making. The overall goal is to enhance the performance and interpretability of models while addressing limitations in data size and computational resources.
Papers
Privacy-Preserving in Medical Image Analysis: A Review of Methods and Applications
Yanming Zhu, Xuefei Yin, Alan Wee-Chung Liew, Hui Tian
Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods
Dennis Wei, Inkit Padhi, Soumya Ghosh, Amit Dhurandhar, Karthikeyan Natesan Ramamurthy, Maria Chang
Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization
Yury Demidovich, Petr Ostroukhov, Grigory Malinovsky, Samuel Horváth, Martin Takáč, Peter Richtárik, Eduard Gorbunov
Jailbreak Defense in a Narrow Domain: Limitations of Existing Methods and a New Transcript-Classifier Approach
Tony T. Wang, John Hughes, Henry Sleight, Rylan Schaeffer, Rajashree Agrawal, Fazl Barez, Mrinank Sharma, Jesse Mu, Nir Shavit, Ethan Perez