📐 Transcribe handwritten math into accurate LaTeX using a modular Vision-Language Model fine-tuning pipeline for efficient training on consumer GPUs.

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

🌟 Build a PyTorch implementation of Google's PaliGemma model for advanced vision-language tasks, including object detection and segmentation.

🌳 Run multiple isolated Claude Code instances in Docker containers, ensuring automatic branch management and full development environments for simultaneous tasks.

🔍 Explore GEMM: a C/C++ library for efficient matrix multiplication using OpenMP, designed for parallel computing learners and practitioners.

👁️ Deploy YOLO11 for efficient computer vision on edge devices, optimized for the Horizon X5 RDK with a streamlined C++ codebase.

Foundation-Models chat app tutorial for iOS with on-device LLMs, tools, and chat. Shows on-device inference with FoundationModels and calendar tool use. 🐙

A collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL.

A collection of guides and examples for the Gemma open models from Google.

streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL

A collection of guides and examples for the Gemma open models from Google.

Fine-tuning Google PaLiGemma for specialized downstream vision-language tasks

A production-ready, modular fine-tuning pipeline for converting handwritten mathematical expressions into LaTeX using Google's PaliGemma 3B and QLoRA.

VL-JEPA (Vision-Language Joint Embedding Predictive Architecture) in MLX

PyTorch implementation of Google's PaliGemma vision-language model with VQ-VAE decoder for processing referring expression segmentation outputs. Supports detection, segmentation, VQA, and captioning.

vision language models finetuning notebooks & use cases (Medgemma - paligemma - florence .....)

PyTorch implementation of Google’s Paligemma VLM with SigLip image encoder, KV caching, Rotary embeddings and Grouped Query attention . Modular, research-friendly, and easy to extend for experimentation.

This repository contains the project of the lecture DI725

PaLiGemma from-scratch implementation

This repository contains code for fine-tuning Google's PaliGemma vision-language model on the Flickr8k dataset for image captioning tasks