AI
Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions
Researchers have found that large language models can be unstable and sensitive to subtle changes in...
AI
CentaurBench: Benchmarking LLM Capabilities on Augmenting vs. Automating Real-World Work Tasks
Researchers have developed a new benchmarking framework called CentaurBench to evaluate the capabili...
AI
Performance Drift Detection in Machine Learning as a Service (MLaaS) for IoT Environments
Researchers have proposed a framework for detecting performance drift in Machine Learning as a Servi...
AI
MorphoGP: A Nonparametric Framework for Predicting Equilibrium Beach Profiles Under Tidal Influence
Researchers have developed a new framework called MorphoGP to predict equilibrium beach profiles und...
AI
The Role of Grid Cells in Reducing Spatial Aliasing in Hippocampal Place Representations
Researchers have found a way to reduce spatial aliasing in hippocampal place rep...
AI
MR-IQA-2: Faithful Image Quality Reflection via Fine-Grained Credit Assignment
Researchers have proposed a new framework called MR-IQA-2 for image quality asse...
AI
From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning
Researchers have developed a new method called VAKE to help Large Language Model...
AI
OmniHandwritingOCR: A Diagnostic Benchmark for Evaluating Multimodal LLMs in Handwritten OCR Scenarios
Researchers have introduced OmniHandwritingOCR, a benchmark for evaluating the a...