This repository implements a hybrid sample generation pipeline for imaging data to extend existing training datasets.

4-GPU H800 low-resource post-training optimization project for Qwen3.6-35B-A3B MoE.

For me, the goal of this project was to handle transformers fine tuning by implementing and applying optimization training techniques using limited computational resources.

A production-ready adaptive meta-learning framework for continuous self-improvement. airbornehrs (MirrorMind) is a lightweight PyTorch framework that turns standard deep learning models into self-improving systems.

GPU memory-efficient training for PyTorch - 90%+ memory savings through gradient compression

Drop-in, idempotent speed patches for PGSR surface-reconstruction training — removes per-iteration PCIe transfers, redundant ones-kernel convolutions, and GPU-CPU logging syncs (plus a real EMA-logging bug) with CPU-proven numerical parity: same geometry, lower GPU bill.