LinkedIn's Semantic Search Upgrade, Enabling Large-Scale Retrieval on Edge Devices, and More!

Vol.85 for Dec 30, 2024 - Jan 05, 2025

Stay Ahead of the Curve with the Latest Advancements and Discoveries in Information Retrieval.

This week’s newsletter highlights the following research:

1. Building a Personalized Semantic Search Engine for Professional Content at Scale, from LinkedIn

2. A Systematic Survey of KV Cache Optimization for Large Language Models, from Li et al.

3. Efficient Text Embeddings Through Knowledge Distillation and Dimension Reduction, from Zhang et al.

4. Extending LLM Context Length Through Self-Directed Learning, from Microsoft

5. A Generative Approach to Watch Time Prediction in Video Recommendation Systems, from Kuaishou

6. Enabling Large-Scale Retrieval on Edge Devices, from Seemakhupt et al.

7. A Comprehensive Survey of Graph-Enhanced Retrieval-Augmented Generation, from Han et al.

8. High-Quality Data Engineering for Multilingual Embedding Models, from Hu et al.

9. A Study of Systematic SEO Vulnerabilities in Embedding-Based Search, from Tel Aviv University

10. Improving RAG Accuracy Through Multi-Agent Document Filtering, from Visa Research