AI
Stability-Aware Feature Design for Robust Watermark Detection in Machine-Generated Text
Researchers have developed a new method for detecting machine-generated text called Pattern Stabilit...
AI
Operationalizing Narrative Entropy (Sn): A Two-Scene Registered Pilot Report and Pre-Validation Protocol
Researchers have developed a method to quantify the processing load imposed by narrative texts, call...
AI
You Are What You Prompt: Prompt Quality, Domain Shift, and Uncertainty in Agrifood Vision-Language Models
Researchers have studied how well zero-shot classification works in agrifood vision-language models ...
AI
Alignment Is All You Need: Instruction-Free Training for General Audio-Language Models
Researchers have developed an approach to training large language models for multiple audio and text...
AI
Efficient INT8 Inference of Small NLP Models on Server CPUs with PyTorch Native Stack
Researchers have developed a method for efficiently running small natural langua...
AI
Artifact-centered Claim-aware Observability for Autonomous Scientific Agents
A new approach for observing and auditing autonomous scientific agents has been ...
AI
Figurative and Cultural Knowledge in LLMs: Investigating Cross-Domain Transfer through Fine-Tuning
Researchers investigated whether large language models (LLMs) can learn to under...
AI
Tangut Word Segmentation under Extreme Resource Scarcity: Integrating Traditional Lexicons and Unlabeled Text
Researchers have developed a method for segmenting words in the Tangut language,...