🔗 LLM Orchestration - tamaulipas

HistoRAG: Embedding Historical Methodology in Retrieval-Augmented Generation Through Critical Technical Practice

🧠LLMs arxiv.org·

Combining Retrieval-Augmented Text Generation with LLMs for Reading Content Recommendations

⚙️AI Engineering arxiv.org·

Visual Retrieval-Augmented Generation for Silhouette-Guided Animal Art

⚙️AI Engineering arxiv.org·

Ghost Vectors: Soft-Deleted Embeddings Remain Reconstructible in HNSW Vector Databases

⚙️AI Engineering arxiv.org·

A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation

⚙️AI Engineering arxiv.org·

CONCORD: Asynchronous Sparse Aggregation for Device-Cloud RAG under Document Isolation

⚙️AI Engineering arxiv.org·

SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG

⚙️AI Engineering arxiv.org·

SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges

⚙️AI Engineering arxiv.org·

ChatPlanner: A Large Language Model Framework for Personalized Public Transit Routing

⚙️AI Engineering arxiv.org·

SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG

⚙️AI Engineering arxiv.org·

Understanding the Behaviors of Environment-aware Information Retrieval

⚙️AI Engineering arxiv.org·

MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval

⚙️AI Engineering arxiv.org·

Intelligent Multimodal Retrieval and Reasoning for Geospatial Knowledge Discovery on the I-GUIDE Platform

⚙️AI Engineering arxiv.org·

Semantics-Enhanced Retrieval-Augmented Time Series Forecasting

⚙️AI Engineering arxiv.org·

Overcoming the Impedance Mismatch: A Theoretical Roadmap for Fusing Foundation Models and Knowledge Graphs

⚙️AI Engineering arxiv.org·

Building an AI Content Strategy Assistant with LangGraph

Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems

Designing AI Platforms That Scale: A Practical Blueprint

MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation

HistoRAG: Embedding Historical Methodology in Retrieval-Augmented Generation Through Critical Technical Practice

Combining Retrieval-Augmented Text Generation with LLMs for Reading Content Recommendations

Visual Retrieval-Augmented Generation for Silhouette-Guided Animal Art

Ghost Vectors: Soft-Deleted Embeddings Remain Reconstructible in HNSW Vector Databases

A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation

CONCORD: Asynchronous Sparse Aggregation for Device-Cloud RAG under Document Isolation

SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG

SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges

ChatPlanner: A Large Language Model Framework for Personalized Public Transit Routing

SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG

Understanding the Behaviors of Environment-aware Information Retrieval

MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval

Intelligent Multimodal Retrieval and Reasoning for Geospatial Knowledge Discovery on the I-GUIDE Platform

Semantics-Enhanced Retrieval-Augmented Time Series Forecasting

Overcoming the Impedance Mismatch: A Theoretical Roadmap for Fusing Foundation Models and Knowledge Graphs

NeuroSymbolic AI for Legal AI-TRISM: Trustworthy, Reliable, Interpretable, Safe Models