AI
Detecting Backdoors in Object Detection via Pre-NMS Prediction Distribution Shift
Researchers have proposed a method called DistScan to detect backdoors in object detection models. A...
AI
Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation
Researchers have developed a new framework called Open-MOPD to address the issue of capability imbal...
AI
Discretizing Continuous Time Series for Imputation with Masked Diffusion Training
Researchers have proposed a new method for imputing missing values in time series data. The Masked D...
AI
PGFS++: Molecular Property Improvement under Synthesis and Diversity Constraints
Researchers have developed a new AI framework called PGFS++, which can improve the properties of mol...
AI
Intercepting the Kangaroo: Experimental Astrolinguistics with Constructed Lexicons, Active Probing, and Large Language Models as Informants and Hypothesis Proposers
Researchers have developed an experimental framework for communicating with enti...
AI
Leaf Values as Coordinates: Exact Contrastive Explanation for Gradient-Boosted Ensembles
Researchers have found a way to interpret the predictions made by gradient-boost...
AI
Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets
Researchers have developed a method to distribute large language models across m...
AI
Interpretable AI predicts a 2026 summer dry anomaly in central China
Researchers have developed a deep learning model that can predict seasonal preci...