Qin Liu

@lqhl

Software Engineer at MyScale

Joined May 2022

About

I am Qin Liu, a software engineer with a deep passion for computer systems and artificial intelligence. Currently, I work at MyScale, a fully-managed vector database company, focusing on vector databases and retrieval-augmented generation (RAG).

Available for

Nothing here yet.

Qin Liu's blogs

Qin Liu's Blogblog.lqhl.me6 posts

Articles Comments

Recently published

QLQin Liublog.lqhl.meAug 8, 2025 · 5 min read

Exploring AI Memory Architectures (Part 3): From Prototype to Blueprint

1. Connecting Blueprints and Prototypes In the first two posts, we saw an idea evolve from a micro-architecture to a macro-system. Memory³ was like a detailed chip schematic, defining an efficient "memory circuit." MemOS was like a grand urban plan, ...

0

QLQin Liublog.lqhl.meAug 8, 2025 · 6 min read

Exploring AI Memory Architectures (Part 2): MemOS Framework

Paper: MemOS: A Memory OS for AI SystemLink: https://arxiv.org/abs/2507.03724v2GitHub: https://github.com/MemTensor/MemOS 1. From Data Structure to Operating System In the last post, we saw how Memory³ designed an efficient "memory data structure." B...

0

QLQin Liublog.lqhl.meAug 8, 2025 · 5 min read

Exploring AI Memory Architectures (Part 1): A Deep Dive into Memory³

Paper: Memory³: Language Modeling with Explicit MemoryLink: https://arxiv.org/abs/2407.01178v1 1. The Third Path for Knowledge Large language models learn in two ways. The first is parametric memory. Knowledge gets encoded into the model’s billions o...

1

U

QLQin Liublog.lqhl.meAug 8, 2024 · 7 min read

Mem0: How Three Prompts Created a Viral AI Memory Layer

In the rapidly evolving world of artificial intelligence, Mem0 has emerged as a standout project, garnering over 19,000 stars on GitHub. This innovative system aims to enhance AI's ability to learn continuously and adapt to individual user needs thro...

1

M

QLQin Liublog.lqhl.meJan 19, 2024 · 4 min read

Filtered Vector Search: A Key Technology in RAG Systems

Basically, in an Retrieval-Augmented Generation (RAG) system, documents (including texts, PDFs, Word, PPTs, etc.) are initially processed through chunking to extract embedding vectors, which are then stored and indexed in a vector database. When a us...

0

Qin Liu

About

Available for

Qin Liu's blogs

Recently published

Exploring AI Memory Architectures (Part 3): From Prototype to Blueprint

Exploring AI Memory Architectures (Part 2): MemOS Framework

Exploring AI Memory Architectures (Part 1): A Deep Dive into Memory³

Mem0: How Three Prompts Created a Viral AI Memory Layer

Filtered Vector Search: A Key Technology in RAG Systems

Search Hashnode

Qin Liu

About

Available for

Qin Liu's blogs

Recently published

Exploring AI Memory Architectures (Part 3): From Prototype to Blueprint

Exploring AI Memory Architectures (Part 2): MemOS Framework

Exploring AI Memory Architectures (Part 1): A Deep Dive into Memory³

Mem0: How Three Prompts Created a Viral AI Memory Layer

Filtered Vector Search: A Key Technology in RAG Systems