Researchers have developed a new framework for detecting deepfakes that provides interpretable justifications. The approach, called Feature-robust Aug...
Machine translation evaluation methods often rely on reference-based metrics, which can be biased and unfair to systems that preserve the source meani...
Researchers have proposed MentorPulse, a method for refreshing cross-model latent guidance in long-form generation tasks. This approach addresses the ...
Researchers have developed a new system for planning flight paths in complex environments. The Neural-Primitive system uses imitation learning to gene...
Researchers have developed a method to recover compressed and quantized large language models (LLMs) called Quantization-Aware Healing (QAH). This app...
Researchers from Vibe Coding studied whether explicitly requesting security best practices improves web application generation. They generated six dis...
Researchers have developed a new AI model called SAraBERT for summarizing Arabic documents. The model includes inter-sentence transformer layers to im...
Researchers studied whether large language models (LLMs) can perform structured security reasoning in cybersecurity workflows. They used real-world th...
Researchers have developed WA-JEPA, a new approach to autonomous driving planning that improves upon the existing Video Joint Embedding Predictive Arc...
Researchers have proposed a new method to improve the robustness of large language models when they are quantized, or converted into lower-precision f...
Researchers have developed a method called Doubt-Preserving Quantization (DPQ) to preserve uncertainty in language models when they are quantized for ...
Researchers have evaluated three lightweight language models (LLMs) - Claude-Haiku-4.5, GPT-5.4-Mini, and Gemini-3.1-Flash-Lite - for their ability to...