Skip to content
View AndreAmaduzzi's full-sized avatar
🎯
Focusing
🎯
Focusing

Highlights

  • Pro

Block or report AndreAmaduzzi

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
AndreAmaduzzi/README.md

Hi there 👋

Hi everyone, I'm Andrea Amaduzzi, for friends Ama. I've been exploring the wonders of technology since my first encounter with a computer. I graduated in Automation Engineering with top honors from the University of Bologna, after spending an amazing semester abroad at the University of Technology of Sydney, Australia and my Master's thesis internship at KUKA - Corporate Research in Augsburg, Germany. Currently, I'm a 3rd-year PhD student at the University of Bologna's Computer Vision Lab (CVLAB), where I work at the exciting intersection of Computer Vision and NLP, with a focus on 3D data and large language models.

I'm also passionate about teaching, currently serving as a Teaching Assistant for the courses of "Image Processing and Computer Vision" and "Logic Design".

I’m on the hunt for research internship opportunities — and while I may be the only Italian who doesn’t drink coffee, I promise my energy levels are fueled by pure curiosity and a sprinkle of determination!

If you want to know more about my research work, check out my personal website!

Projects I've Worked On 🚀

Throughout my journey, I've dabbled in some pretty cool projects! Here’s a snapshot:

  • Sydney Adventures 🌏: During my semester at UTS, I teamed up with a mobile robot to explore and map the vast Building 11 (those who studied there know just how large it is!). I became best friends with C++ (sacrificing my sleep and my desire to surf at Bondi Beach) as we conquered the unknown corners of campus together!
  • KUKA Chronicles, Part I 🤖: In Augsburg, I had the chance to teach a robot how to observe and understand human activities. Yes, the robot had eyes! Using Python, ROS, and C++, I made sure it could keep up with the human in front of it (no judgment on who was faster at learning).
  • KUKA Chronicles, Part II 🛠️: My robot and I weren’t done! Next, we scanned an object and generated its mesh together, collaborating like two sci-fi protagonists. Java and Python were my trusty sidekicks on this mission.
  • Computer Vision Shenanigans 🖼️: Over time, I’ve tackled a bunch of other Computer Vision projects, from generating a point cloud from text to describing it using natural language. I also got my hands dirty with the classics: image classification, detection, and, of course, having lots of fun with 3D data (Python to the rescue!).
  • Datalogic Adventures 📦: At Datalogic, I designed and maintained image processing algorithms for decoding all sorts of barcodes. Insiders know there are tons of different kinds of barcodes, and reading them all under various lighting conditions is like trying to find Waldo in a crowd! I even tackled some tricky issues in airport barcode scanners for luggage—so if your bags arrived on time during your last trip, you can thank me (and my algorithms)...
  • Current PhD Madness 📚: These days, I’m deep into 3D data and language models, working to help machines make sense of our 3D world through the magic of language. It's like teaching a robot how to see and describe our reality, but with way more Python and cutting-edge machine learning libraries!

Technologies I Love Working With 💻

I have a deep interes for AI, especially when it comes to exploring how machines perceive and understand the world. Here’s a glimpse into the tools I use every day:

  • Python
  • PyTorch
  • Huggingface Transformers
  • CUDA
  • OpenCV
  • TensorFlow
  • NumPy
  • C++
  • Bulleted points, as you may have noticed

In my current research, I combine 3D data representations and Large Language Models, in order to understand and reason about our 3D world using language. I also focus on computer vision algorithms, rendering 3D models, and processing visual data.

My repositories 💾

On my GitHub page, you'll find the code from my published papers, along with all the projects I've worked on — most of which were crafted during late-night, sleep-deprived PhD marathons. You can also find some open-source projects I contributed to... with a bit more daylight!

When I'm Not Coding... ⚽🏐📚

When I’m not wrangling code or training machines to understand the world, you’ll probably find me:

  • Getting Lost in Literature 📖: I’m currently battling my way through Proust’s In Search of Lost Time (À la recherche du temps perdu). It’s a bit like my PhD… long, intricate, and sometimes I wonder if it will ever end. But hey, if Dostoevskij didn't scare me off, nothing will! And, by the way, what's better than a good existential crisis to keep things balanced, right?
  • Spiking on the Beach 🏐: When I'm not deep in code, you can find me on the sand, spiking balls and pretending I'm a pro beach volleyball player.
  • Cheering for Bologna FC ❤️💙: As a proud supporter of Bologna Football Club, I believe in cheering for my city’s team no matter what. Whether we're scoring goals or... "making experience playing the Champions League". Forza Bologna!

Let's talk!👂

You can find me on a looooong list of social networks. These are the ones I don't feel ashamed sharing 😬

Linkedin X

Feel free to reach out if you'd like to chat about research, AI, or just technology in general.

Pinned Loading

  1. AndreAmaduzzi.github.io AndreAmaduzzi.github.io Public

    Andrea Amaduzzi personal website

    CSS 1

  2. Infusion Infusion Public

    Python 1

  3. CrossCoherence CrossCoherence Public

    Official code for "Looking at words and points with attention: a benchmark for text-to-shape coherence" ICCV Workshops 2023

  4. kuka_action_recognition kuka_action_recognition Public

    ROS project for the recognition of human actions, from RGBD input

    Jupyter Notebook

  5. CVLAB-Unibo/LLaNA CVLAB-Unibo/LLaNA Public

    Official code repository of LLaNA: Large Language and NeRF Assistant

    Python 7