Enhancing Encoder Speech Models with Text-Only Data
Discover how integrating text-only data boosts encoder-based speech recognition accuracy and efficiency in modern models.
Detecting Alignment Faking in LLMs via Tool Selection
Explore how Tatemae detects alignment faking in large language models by analyzing tool selection to improve AI safety and reliability.
Efficient Edge-Cloud Vision-Language Models with Semantic Communication
Discover a progressive semantic communication framework that optimizes edge-cloud vision-language models for low-latency, bandwidth-efficient AI inference.
Tree-of-Text: Efficient Table-to-Text Sports Reporting AI
Discover Tree-of-Text, a novel AI framework that enhances table-to-text generation for accurate, fast sports game reports with reduced cost and time.
GenAI Risks for Youth in Saudi Arabia: Cultural Insights
Explore culturally aware GenAI risks for youth in Saudi Arabia, highlighting privacy, safety, and design recommendations from parents and teachers.