fede.ai Open in urlscan Pro
45.79.155.95  Public Scan

Form analysis
0 forms found in the DOM

Text Content

FEDERICO CASSANO

Researcher
with interests in artificial intelligence, programming languages, and security.

 * 
 * 
 * 
 * 




ABOUT ME

Ciao! I'm Federico, a computer science researcher from Milan, Italy, working as
a Research Scientist at Anysphere, improving Cursor's code generation models.

My research focuses on advancing automated software engineering, with the
ultimate goal of fully automating the programming process. I believe software
should be customized to each individual's needs, rather than taking a
one-size-fits-all approach that serves billions of users with the same solution.

To further this goal, I co-founded GammaTau AI, an independent group of 40+
researchers dedicated to democratizing access to programming through AI.
Additionally, I'm an active contributor to the BigCode project, which is
responsible for developing the StarCoder family of large language models.

Prior to Cursor, I held research positions at Scale AI, Roblox, Trail of Bits,
and Prof. Arjun Guha's research lab at Northeastern University.

I'm also honored to have served as the captain of the highly skilled NUCCDC
cybersecurity team, which has claimed the NECCDC championship title for three
consecutive years.

Produces the nth Fibonacci number. Uses a helper with an accumulator. Generate




MultiPL-T'd 1b model running on a single CPU core!


ACADEMIC PORTFOLIO


AWARDS

 * CRA Outstanding Undergraduate Researcher Award Finalist (2024)
    * Nominated as one of the top undergraduate CS researchers in the USA

 * Northeast Collegiate Cyber Defense Competition (NECCDC) Champion (2021-2024)
    * Won the regional competition for the past three years in a row

 * Hudson Alpha Tech Challenge 1st (2021)
    * Won the national hackathon with a team of 4 high schoolers

 * National Cyber League 2021 Top 1% (2021)
    * Placed in the top 1% of the national competition as a high schooler


PUBLICATIONS

 * SelfCodeAlign: Self-Alignment for Code Generation
    * Yuxiang Wei, Federico Cassano, Jiawei Liu, Yifeng Ding, Naman Jain,
      Zachary Mueller, Harm de Vries, Leandro Von Werra, Arjun Guha, Lingming
      Zhang
    * Neural Information Processing Systems (NeurIPS), 2024.
      
      

 * Planning In Natural Language Improves LLM Search For Code Generation
    * Evan Z Wang, Federico Cassano, Catherine Wu, Yunfeng Bai, William Song,
      Vaskar Nath, Ziwen Han, Sean M. Hendryx, Summer Yue, Hugh Zhang
    * preprint arXiv:2409.03733 (arXiv), 2024.
      
      

 * StarCoder 2 and The Stack v2: The Next Generation
    * Anton Lozhkov, Raymond Li, Loubna Ben Allal, Federico Cassano, Joel
      Lamy-Poirier, Nouamane Tazi, et al.
    * preprint arXiv:2402.19173 (arXiv), 2024.
      
      

 * Can It Edit? Evaluating the Ability of Large Language Models to Follow Code
   Editing Instructions
    * Federico Cassano, Luisa Li, Akul Sethi, Noah Shinn, Abby Brennan-Jones,
      Anton Lozhkov, Carolyn Jane Anderson, Arjun Guha
    * The First Conference on Language Modeling (COLM), 2024. (acceptance rate:
      28%)
      
    * The First International Workshop on Large Language Model for Code (ICSE
      Workshop), 2024.
      

 * Knowledge Transfer from High-Resource to Low-Resource Programming Languages
   for Code LLMs
    * Federico Cassano, John Gouwar, Francesca Lucchetti, Claire Schlesinger,
      Carolyn Jane Anderson, Michael Greenberg, Abhinav Jangda, Arjun Guha
    * ACM SIGPLAN Conference on Object-Oriented Programming, Systems, Languages,
      and Applications (OOPSLA), 2024. (acceptance rate: 29%)
      
      

 * Reflexion: Language Agents with Verbal Reinforcement Learning
    * Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik
      Narasimhan, Shunyu Yao
    * Neural Information Processing Systems (NeurIPS), 2023. (acceptance rate:
      26%)
      
      

 * MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code
   Generation
    * Federico Cassano, John Gouwar, Daniel Nguyen, Sydney Nguyen, Luna
      Phipps-Costin, Donald Pinckney, Ming-Ho Yee, Yangtian Zi, Carolyn Jane
      Anderson, Molly Q Feldman, Arjun Guha, Michael Greenberg, Abhinav Jangda
    * ACM Joint European Software Engineering Conference and Symposium on the
      Foundations of Software Engineering (ESEC/FSE), 2023.
      
    * IEEE Transactions on Software Engineering (TSE), 2023.
      

 * Type Prediction With Program Decomposition and Fill-in-the-Type Training
    * Federico Cassano, Ming-Ho Yee, Noah Shinn, Arjun Guha, Steven Holtzen
    * preprint arXiv:2305.17145 (arXiv), 2023.
      
      

 * npm-follower: A Complete Dataset Tracking the NPM Ecosystem
    * Donald Pinckney, Federico Cassano, Arjun Guha, Jonathan Bell
    * ACM Joint European Software Engineering Conference and Symposium on the
      Foundations of Software Engineering (ESEC/FSE), 2023.
      
      

 * A Large Scale Analysis of Semantic Versioning in NPM
    * Donald Pinckney, Federico Cassano, Arjun Guha, Jonathan Bell
    * 20th International Conference on Mining Software Repositories (MSR), 2023.
      (acceptance rate: 36%)
      
      

 * Flexible and Optimal Dependency Management via Max-SMT
    * Donald Pinckney, Federico Cassano, Arjun Guha, Jonathan Bell, Massimiliano
      Culpo, Todd Gamblin
    * IEEE/ACM International Conference on Software Engineering (ICSE), 2023.
      (acceptance rate: 26%)
      
      

 * SafeLLVM: LLVM Without The ROP Gadgets!
    * Federico Cassano, Charles Bershatsky, Jacob Ginesin, Sasha Bashenko
    * preprint arXiv:2305.06092 (arXiv), 2023.
      
      

Contact me: federico [dot] cassano [at] federico [dot] codes