-
IET-1, Forschungszentrum Jülich
- Jülich, Germany
-
09:31
(UTC +02:00) - https://www.linkedin.com/in/amir-omidvarnia/
- https://orcid.org/0000-0002-4744-8721
- @AOmidvarnia
Highlights
- Pro
Stars
Biomni: a general-purpose biomedical AI agent
AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.
Website Template this repository is free for all. You can use this code for both personal & commercial use.
🎏 A curated collection of all country flags in SVG — plus the CSS for easier integration
A beautiful, simple, clean, and responsive Jekyll theme for academics, with support for multiple languages
170 HTML5 Website Templates - free editable templates
High-Resolution Image Synthesis with Latent Diffusion Models
Cookiecutter template for a Python package.
A logical, reasonably standardized, but flexible project structure for doing and sharing data science work.
A cross-platform command-line utility that creates projects from cookiecutters (project templates), e.g. Python package projects, C projects.
A lightweight, powerful framework for multi-agent workflows
Official electron build of draw.io
A curated list of awesome TikZ documentations, libraries and resources
The python library for real-time communication
FakET: Simulating Cryo-Electron Tomograms with Neural Style Transfer
Google Research
Large-Scale Multimodal Dataset of Astronomical Data
Prompt-To-Agent : Create custom engineering agents for your codebase
🪄 Create rich visualizations with AI
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
Latex code for making neural networks diagrams
🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.
The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
A chronological (up to the century in which the poet has lived) of Persian poetry, extracted from the brilliant Ganjoor database
A Persian Poet Transformer! (finetuned GPT2 on Ganjoor data)
Keras documentation, hosted live at keras.io
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
The simplest, fastest repository for training/finetuning medium-sized GPTs.