AI
The Metanym Game: An LLM Benchmark Without Ground Truth That Rises With the Models It Measures
Researchers have developed a new benchmark for evaluating large language models (LLMs), called the M...
AI
Know2Guess: A Contamination-Aware Multi-Zone Benchmark for Knowledge-Boundary Evaluation in Large Language Models
A new benchmark called Know2Guess has been developed to evaluate the reliability of large language m...
AI
MatMMExtract: An Open-Source Pipeline for Panel-Level Extraction of Grounded Image-Text Pairs from Materials Science Literature
Researchers have developed an open-source pipeline called MatMMExtract that extracts image-text pair...
AI
The Dual Nature of LLM Persona: Aggregated Tendencies and Frame-Dependent Geometry
Researchers have found that Large Language Model (LLM) personalities can be understood in two differ...
AI
What a World Model Represents Is Three Questions
A new paper explores how world models in AI learn task-relevant information thro...
AI
MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents
Researchers have developed MM-ToolSandBox, a framework for evaluating visual too...
AI
Skillware: A Software Ontology and Engineering Lifecycle for Persistent Behavioral Artifacts
A new software ontology called Skillware has been introduced to define persisten...
AI
Looks Right, Works Right: A Project-Level Benchmark for Multi-Screen Mobile App Generation
Researchers have created a new benchmark called MobileForge to evaluate the abil...