AI
BC-Bench: Evaluating Agentic Engineering in a Domain-Specific Language for ERP
Researchers have created a benchmark called BC-Bench to evaluate how well artificial intelligence sy...
AI
KREL: Automatic Medical Coding via Knowledge-Guided Reasoning over Clinical Evidence with LLMs
Researchers have proposed a new framework called KREL for automatic medical coding, which involves a...
AI
Explainable Deepfake Detection with Feature-robust Augmentation and Evidence-grounded Explanation Optimization
Researchers have developed a new framework for detecting deepfakes that provides interpretable justi...
AI
Source-Free MT Evaluation Is Not MT Evaluation
Machine translation evaluation methods often rely on reference-based metrics, which can be biased an...
AI
MentorPulse: Refreshing Cross-Model Latent Guidance for Long-Form Generation
Researchers have proposed MentorPulse, a method for refreshing cross-model laten...
AI
Neural-Primitive: An Efficient End-to-end Local Planner with Primitive-based Imitation Learning for Autonomous Flight
Researchers have developed a new system for planning flight paths in complex env...
AI
Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs
Researchers have developed a method to recover compressed and quantized large la...
AI
Vibe Coding and Web Application Security: A Twin-Prompt Study
Researchers from Vibe Coding studied whether explicitly requesting security best...