Posts by Shaghayegh Roohi

VLM Fine-Tuning for Robotics on AMD Enterprise AI Suite

Vision-language models (VLMs) power applications from image captioning to robotics instruction following, but full model fine-tuning is resource-intensive and slow. Low-Rank Adaptation (LoRA) offers a faster, more efficient alternative by training only a small set of injected parameters while keeping the base model frozen.

Read more ...


Elevating 3D Scene Rendering with GSplat

In this blog we explore how to use GSplat, a GPU-optimized Python library for training and rendering 3DGS models, on AMD devices. This tutorial will guide you through training a model of a scene from a set of captured images, which will then allow you to render novel views of the scene. We use a port of the original GSplat code that has been optimized for AMD GPUs. The examples used throughout this blog were trained and rendered using an AMD MI300X GPU.

Read more ...