Controllable anomaly synthesis for industrial and medical imaging: cVAE-generated defects, context-aware placement, and harmonized fusion into real images.
-
Updated
Nov 19, 2026 - Python
Controllable anomaly synthesis for industrial and medical imaging: cVAE-generated defects, context-aware placement, and harmonized fusion into real images.
For me, the goal of this project was to handle transformers fine tuning by implementing and applying optimization training techniques using limited computational resources.
4-GPU H800 low-resource post-training optimization project for Qwen3.6-35B-A3B MoE.
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.
To associate your repository with the training-optimization topic, visit your repo's landing page and select "manage topics."