---
title: "Repro - POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation"
emoji: 🔬
colorFrom: blue
colorTo: green
sdk: static
pinned: false
tags:
 - trackio
 - trackio-logbook
 - open-experiment
 - icml2026-repro
 - paper-et8jpWLUuD
---

# Repro - POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation

An open experiment logbook, published with [Trackio](https://github.com/gradio-app/trackio).