I’m a Ph.D. student working with Prof. Eran Yahav. (I graduated!)
Since August 2021: I am a post-doc at the Language Technologies Institute (LTI) of Carnegie Mellon University, working with Prof. Graham Neubig, and a member of NeuLab.
This website is no longer maintained. My new website is at https://urialon.ml
My research focuses on machine learning and deep learning approaches for modeling, predicting, improving, and generating source code, a field we call Programming Language Processing.
In a nutshell, similarly to the way that Natural Language Processing (NLP) is concerned with computer-modeling of natural language, Programming Language Processing is concerned with modeling programming languages. Programming is difficult, time-consuming, and even expert programmers lookup for online help all the time. Can a model that was trained on millions of examples help us, humans, with these problems? I believe so, and have some ideas in mind.
Previously, I served 7 years as an officer onboard a missile ship in the Israeli Navy. Later, I completed my BSc summa cum laude at the Computer Science Department at the Technion, as an alumnus of The Rothschild-Technion Scholars Program for Excellence. Between 2014-2016 I worked at Microsoft R&D center in Haifa, developing data security services for the cloud. Between June-September of 2018, I interned at Google New-York, researching neural models for speech recognition.
In addition, I hold a B.A. in Humanities.
I am happily married to Lee and father of Gur š
Publications
Preprints
- How Attentive are Graph Attention Networks?
- Single-Node Attack for Fooling Graph Neural Networks
Accepted Papers
- On the Bottleneck of Graph Neural Networks and its Practical Implications
- A Structural Model for Contextual Code Changes
- Adversarial Examples for Models of Code
- Neural Reverse Engineering of Stripped Binaries using Augmented Control Flow Graphs
- Yaniv David, Uri Alon, Eran Yahav
- Appeared in OOPSLA’2020
- [PDF][BibTex][Video][Code]
- Structural Language Models of Code
- Contextual Speech Recognition with Difficult Negative Training Examples
- code2seq: Generating Sequences from Structured Representations of Code
- Uri Alon, Shaked Brody, Omer Levy, Eran Yahav
- Appeared inĀ ICLR’2019: International Conference on Learning Representations
- Online demo: https://code2seq.org
- [PDF][Poster][Code and trained model][Blog][BibTeX]
- code2vec: Learning Distributed Representations of Code
- Uri Alon, Meital Zilberstein, Omer Levy, Eran Yahav
- AppearedĀ in POPL’2019: Principles of Programming Languages
- ACM SIGPLAN Research Highlight
- Online demo:Ā https://www.code2vec.org
- [PDF][Slides] [Video][Blog][Code and trained model][BibTeX]
- A General Path-Based Representation for Predicting Program Properties
- Uri Alon, Meital Zilberstein, Omer Levy, Eran Yahav
- AppearedĀ in PLDI’2018: Programming Languages Design and Implementation
- [PDF][Slides][Video][Blog][BibTeX]
- [JS Code][JS Dataset][Python Dataset]
- [JS embedding]
Technical Reports
- Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
- Jonathan Shen, …, Uri Alon, …
- Participated in development during an internship at Google
- [PDF]
Service
- Program Committee: PLDI’2021, NeurIPS’2020 CAP workshop,Ā AIDM’20, AIDM’19
- Reviewer: ICML’2021, ICLR’2021, NeurIPS’2020, ICLR’2020
Awards
- 2021-2022 – Rothschild Post-Doctoral Fellowship
- 2021-2022 – Fulbright Post-Doctoral Fellowship (declined)
- 2020 – ACM SIGPLAN Research Highlight, “code2vec: Learning Distributed Representations of Code” (POPL’2019)
- 2019 – Jacobs Excellence Scholarship
- 2019 – Faculty Funding Excellence Scholarship
- 2018 – Faculty Funding Excellence Scholarship
- 2016 – Excellent Teaching Assistant
- 2016 – Dean’s Support Excellent Scholarship
- 2016 – Alumnus of the Rothchild-Technion Program for Excellence
- 2015 – SAMBA – CS Excellent Students