Federico Bianchi

Federico Bianchi

Postdoctoral Researcher at Stanford University

Stanford University

Biography

Hello! I am Federico Bianchi, I am a post-doctoral researcher at Stanford University working with Prof. Dan Jurafsky. I am passionate about working across the entire spectrum of AI and more recent generative AI:

My work appeared in different AI venues (AAAI, ACL, ICLR, NAACL, EACL, Nature Medicine). and it has as also been featured in press (Nature, Nature Machine Intelligence, Washington Post) or in company/university media outlets (1, 2, 3, 4).

My GitHub projects have collected thousands stars over the past few years (e.g., Contextualized Topic Models, RecList, FashionCLIP)

I recently joined the Giving What We Can initiative and donate monthly.

Interests
  • Artificial Intelligence
  • Natural Language Processing
  • Capybaras
Education
  • PhD in Computer Science, 2020

    University of Milano-Bicocca

  • MSc in Computer Science, 2016

    University of Milano-Bicocca

  • BSc in Computer Science, 2014

    University of Milano-Bicocca

Outreach

  • 2023 I was invited to an online seminar on Large Language Modeling by Outerbounds. Together with the Outerbounds I published two blog post on tuning instruction models (1, 2)
  • 2023 I shared some opinions on recent generative tech for MIT Technology Review, my paper was also featured in another issue of MIT Technology Review.
  • 2023 Invited to talk about bias in text-to-image models at Pointer Podcast (In Italian. Spotify)
  • 2022 Invited to talk at the Neptune MLOps podcast on testing recommeder systems (Spotify, Youtube)

Research Philosophy

I think scientific research should be easy to access and to replicate. You can find most of my papers on ArXiv and on open access platforms - unfortunately, this is not always possible. The code I write is available online and I try to make it easy to use so that everyone can benefit from it.

I also try to actively participate in scientific communication. I have many blog posts online, explaining different research topics to the public and I am also part of the ComIntArt (Comitato Intelligenza Artificiale) where I do videos for the Italian public (see for example, this video on GPT-3 limits).

Recent Publications

Quickly discover relevant content by filtering publications. You can also look at my Google Scholar profile for an updated list of my publications.
(2023). When and Why Vision-Language Models Behave like Bags-Of-Words, and What to Do About It?. In ICLR.

PDF Cite Code

(2022). Language Invariant Properties in Natural Language Processing. In NLP Power!.

PDF Cite Code

(2022). Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals. Second Workshop on Language Technology for Equality, Diversity and Inclusion at ACL 2022.

Cite Code

(2022). XLM-EMO: Multilingual Emotion Prediction in Social Media Text. 12th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis at EACL 2021.

Cite Code