Paper-Conference

MDPO: Customized Direct Preference Optimization with a Metric-based Sampler for Question and Answer Generation
MDPO: Customized Direct Preference Optimization with a Metric-based Sampler for Question and Answer Generation

Jan 1, 2025

QUITO: Accelerating Long-Context Reasoning through Query-Guided Context Compression
QUITO: Accelerating Long-Context Reasoning through Query-Guided Context Compression

Jul 1, 2024