Enhancing Local and Global Structure in Compressed AI Agent Memory
cs.AI
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/hank08819/LAQ
Terminology
Sources
- Optimization of embeddings storage for RAG systems using quantization and dimensionality reduction techniques
- When Is 0.1% Enough? Analyzing the Combined Effects of Dimensionality Reduction and Quantization on Text Embedding Compression
- BERTopic: Neural topic modeling with a class-based TF-IDF procedure
- Quantifying Local and Global Fidelity of Nonlinear Embeddings
- FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation
- How to Evaluate Dimensionality Reduction? - Improving the Co-ranking Matrix
- CMET: Clustering guided METric for quantifying embedding quality
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
- Text Embeddings by Weakly-Supervised Contrastive Pre-training
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- Differential rank preservation manifold learning
- The Faiss library
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents