Skip to content
View giorgiopiatti's full-sized avatar
🎯
Focusing
🎯
Focusing
  • Switzerland

Highlights

  • Pro

Block or report giorgiopiatti

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
giorgiopiatti/README.md

Hey There


About Me:

I'm Swiss, 24 years old, highly driven and technically proficient machine learning engineer!

CS Master's student working as a Research Assistant, with a focus on large language model (LLM) evaluation and multi-agent simulations. Co-authored 3 papers published at workshops and top-tier conferences, with experience managing the entire research process—from experimental design to publication. Proficient in a wide array of technical tools and programming languages essential for data science and machine learning.

Present:

I’m working as Student Research Assistent with Zhijing Jin at ETH Zürich.

Future:

I am looking for a full time position starting January 2025.

If you're looking for someone that

  • has broad machine learning expertise
  • is able organize and manage large experiments
  • loves to code from 0 to 100 an ML solution then I might be your guy.

Some projects I've worked on recently:

I worked on Multilingual Trolley Problems for Language Models (Paper Under review)

During my Master Thesis I worked on Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents, which resulted in a paper under review. I've created a multi-agent simulation plattform for Large Language Model, Governance of the Commons Simulation to test if LLMs achieve sustainable equilibrium and investigate multi-agent collaboration.

SUBER: An RL Environment with Simulated Human Behavior for Recommender Systems (Paper accepted at ECAI 2024): A framework for synthetic environments that simulate human behavior by harnessing the capabilities of large language models (LLMs). We complement our framework with in-depth ablation studies and demonstrate its effectiveness with experiments on movie and book recommendations. By utilizing LLMs as synthetic users, we introduce a modular and novel framework for training RL-based recommender systems.

Learning to Bluff and Cooperate: RL in Briscola We construced a multi-agent Briscola (italian card game) environment and trained RNN-based agents using reinforcement learning.

Before saying goodbye

If you want to connect with me, feel free to send me a DM on Linkedin!

Pinned Loading

  1. GovSim GovSim Public

    Governance of the Commons Simulation (GovSim)

    Python 23 8

  2. PathFinder PathFinder Public

    PathFinder is a simple prompting library with support for parsing and regex.

    Python 1

  3. SUBER-Team/SUBER SUBER-Team/SUBER Public

    This repository accompanies our research paper titled "An LLM-based Recommender System Environment".

    Python 7

  4. TiCinesi/Dilated-Convolution-for-GCN TiCinesi/Dilated-Convolution-for-GCN Public

    Deep Learning - project (ETH Zürich)

    Python 1

  5. TiCinesi/Collaborative-models-for-Collaborative-Filtering TiCinesi/Collaborative-models-for-Collaborative-Filtering Public

    Computational Intelligence Lab - project (ETH Zürich)

    Python

  6. TiCinesi/Learning-to-Bluff-and-Cooperate TiCinesi/Learning-to-Bluff-and-Cooperate Public

    Foundations of Reinforcement Learning - project (ETH Zürich)

    Jupyter Notebook