LLM 8
- MUVERA: Transforming Multi-Vector Information Retrieval Through Fixed Dimensional Encodings
- HI-SQL: Optimizing Text-to-SQL Systems through Dynamic Hint Integration
- RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning
- Understanding HNSW - Hierarchical Navigable Small World
- On test-time compute for language models
- Retrieval Augmented Generation and Beyond
- RAG Foundry: A Framework for Enhancing LLMs for RAG
- Model Collapse in AI