Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion Paper • 2609.24220 • Published Sep 21 • 49
Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction Paper • 2609.13285 • Published Sep 8 • 64
Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention Paper • 2606.20945 • Published Jun 18 • 66
Web Retrieval-Aware Chunking (W-RAC) for Efficient and Cost-Effective Retrieval-Augmented Generation Systems Paper • 2604.04936 • Published Jan 8 • 23