Skip to content
View AndreAmaduzzi's full-sized avatar
🎯
Focusing
🎯
Focusing
5 followers · 4 following

Achievements

Achievement: Starstruck

Achievements

Achievement: Starstruck

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
AndreAmaduzzi/README.md

Hi, I'm Andrea Amaduzzi 👋

I recently completed my PhD in Computer Vision at the University of Bologna, where I worked on Multimodal AI for 3D-Language Understanding under Prof. Luigi Di Stefano. During my PhD, I also worked as Research Intern at Niantic Spatial in London, working on spatial reasoning with multimodal LLMs.

My research focuses on teaching machines to understand and reason about the 3D world through language — bridging vision, language, and spatial understanding with large-scale multimodal models.

🔗 Website · Google Scholar · LinkedIn

Research Papers & Code

Paper Venue Code
Spatially-aware Weights Tokenization for NeRF-Language Models NeurIPS 2025 CVLAB-Unibo/Spatial-LLaNA
Scaling LLaNA Under review, IEEE TPAMI Coming soon
LLaNA: Large Language and NeRF Assistant NeurIPS 2024 CVLAB-Unibo/LLaNA
Looking at words and points with attention ICCV 2023 Workshop AndreAmaduzzi/CrossCoherence

What I work with

Python · PyTorch · Hugging Face Transformers · DeepSpeed · FSDP · CUDA · C++ · SLURM · Linux

Experienced in large-scale distributed training on GPU clusters (trained 10B+ parameter models on LEONARDO, a top-10 global supercomputer).

I'm currently exploring full-time Research Scientist and ML Engineer roles. Feel free to reach out at amaduzziandrea@gmail.com.

Pinned Loading

  1. CrossCoherence CrossCoherence Public

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

    1

  2. CVLAB-Unibo/LLaNA CVLAB-Unibo/LLaNA Public

    Official code repository of LLaNA: Large Language and NeRF Assistant

    Python 19

  3. CVLAB-Unibo/Spatial-LLaNA CVLAB-Unibo/Spatial-LLaNA Public

    [NeurIPS 2025] Spatially-aware Weights Tokenization for NeRF-Language Models

    Python 3

  4. AndreAmaduzzi.github.io AndreAmaduzzi.github.io Public

    Andrea Amaduzzi personal website

    CSS 1