HAN XIZE / XUZETOP1

Turning ideas into code.Taking problems into research.

Exploring the space between local AI, hybrid retrieval, and agent tooling. This is where I keep my open-source projects — and the code and materials that make research checkable.

Hunan Institute of Information Technology
China · 5 public projects
Python / TypeScript

01 / SELECTED PROJECTS

Open-source projects

Ongoing work across AI applications, developer tools, and research reproduction.

AI app01

Teacher

A local AI learning companion for desktop and Android that connects private document retrieval, knowledge tracing, on-device analysis, and LAN sync.

TypeScriptLocal-firstRAG
Dev tool02

llm-cache-optimizer

An agent cache runtime for LLM applications that brings cache awareness into the application's execution flow and provides groundwork for cache-related development.

PythonLLMCache Runtime
Dev tool03

Harnesies_bridge

An orchestration bridge across coding agent tools — Codex, Claude Code, OpenCode, and Qwen — with isolation, audit, and approval mechanisms.

TypeScriptOrchestrationAgents
Research tool04

research-workbench

AI research assistance for topic selection, experiment design, paper outlining, citation auditing, and iterative review — helping researchers organise work and check their arguments.

Research WorkflowCitation Audit
Reproduction05

RAG_RRF

Public reproduction materials for offline hybrid retrieval evaluation, comparing BM25, dense retrieval, and RRF within a unified candidate space, with frozen rankings, labels, analysis code, and figures.

PythonBGE-M3RRF

Showing all 5 projects

02 / ACADEMIC & RESEARCH

Research that
leaves checkable material.

Focused on retrieval methods, evaluation process, and the boundaries of reproduction. Research materials and publication details are listed separately.

Open research materials

Lightweight hybrid retrieval evaluation in a unified candidate space

Combining SQLite FTS5 BM25, BGE-M3 dense retrieval, and RRF, with frozen inputs and the analysis pipeline published so that offline evaluation results can be verified.

The manuscript has been accepted; the public materials keep the frozen inputs, analysis pipeline, and figures, but not the raw corpus — see the repository notes for the scope of reproduction.

Read the research materials and reproduction notes
Accepted · Conference paperMLEIL-2026-000070

Lightweight Embedded Hybrid Retrieval for Local LLMs: Unified Candidate Space and Deployment Trade-offs

Xize Han, Xin Xie

The International Conference on Machine Learning, Embodied Intelligence and Large Models (MLEIL 2026) · Accepted for the conference proceedings; the proceedings will be submitted to EI for potential indexation, subject to official publication

Within a unified candidate space of 1,696 educational entities, we compare SQLite FTS5, BGE-M3 dense retrieval, and RRF fusion. Over 93 questions and 186 query instances, RRF reaches NDCG@5 0.8916 and MRR@5 0.9330 — 0.1124 and 0.1781 above Dense and BM25 respectively. A fixed-list quota ablation further shows how deployment source policy changes top-five coverage and graded ranking.

View paper PDFAuthor version · 10 pages · 1.0 MB

© 2026 Xize Han, Xin Xie. This is the author's version of a paper accepted for publication in the Proceedings of MLEIL 2026.

03 / ABOUT

Han Xize

My public projects revolve around local AI applications, retrieval evaluation, and agent tooling: tools that serve a real problem, and records that let an experiment be revisited and checked.

Implementations, research materials, and repository documentation live on GitHub.